© 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. 575
    Prev
    Next
    INDEX
    Explanations

    items combined

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

    The neuron responds to numeric tokens (multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered 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
    raco
    -0.92
     also
    -0.81
     and
    -0.79
    小声
    -0.77
     at
    -0.77
    ργασ
    -0.77
    🦰
    -0.76
    कर्ष
    -0.76
     or
    -0.75
    lesias
    -0.75
    POSITIVE LOGITS
     together
    6.03
     combined
    5.00
    Together
    4.97
    together
    4.75
     Together
    4.69
     collectively
    4.41
    combined
    4.22
    Combined
    3.98
     juntos
    3.95
     TOGETHER
    3.95
    Activations Density 0.213%

    No Known Activations