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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31710
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

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

    The neuron activates on numeric tokens, detecting sequences of digits such as phone numbers, years, addresses, or other 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
     🙏
    -0.84
    rather
    -0.82
    timedia
    -0.77
    कु
    -0.74
    $=
    -0.73
     Huerta
    -0.73
     rather
    -0.71
     situations
    -0.70
    ឥ
    -0.69
    efs
    -0.69
    POSITIVE LOGITS
    ToUse
    0.83
     complements
    0.82
    工资
    0.78
    につき
    0.78
    ញ
    0.74
    glEnable
    0.73
    才可以
    0.73
    まぁ
    0.73
    ultan
    0.72
    mbitos
    0.72
    Activations Density 0.090%

    No Known Activations