© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33587
    Prev
    Next
    INDEX
    Explanations

    telephone numbers or contact details

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting sequences of digits—particularly phone‐number–style numeric strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phone numbers and contact information formatting, particularly around colons, spacing, and numerical digits in telecommunication contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    contact details, especially telephone numbers and their formatted digit strings (including symbols like plus signs, dashes, and parentheses).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Consejos
    -0.89
    Besos
    -0.85
    ærer
    -0.82
    iją
    -0.81
     グリーン
    -0.81
    isNew
    -0.77
     Divider
    -0.74
    ناسب
    -0.74
    ㈦
    -0.73
    *}\
    -0.73
    POSITIVE LOGITS
     +
    3.47
     (+
    2.97
     $+
    2.66
    (+
    2.34
    +
    2.27
     +(
    2.14
     [+
    2.00
    $+
    1.95
    }+
    1.94
     "+
    1.84
    Activations Density 0.011%

    No Known Activations