© 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. 22-GEMMASCOPE-RES-131K
    7. 68454
    Prev
    Next
    INDEX
    Explanations

    code examples and names

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

    The neuron fires on numeric‐related tokens—digits, numeric literals, format specifiers, and numeric function/method names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    etron
    -0.98
    ciech
    -0.97
    гів
    -0.96
    avril
    -0.95
     bereiken
    -0.92
     รวม
    -0.92
     trekken
    -0.92
    lussen
    -0.91
     Cette
    -0.90
    intended
    -0.90
    POSITIVE LOGITS
    이며
    1.02
    ophyta
    0.93
    //-
    0.91
    //----
    0.91
     chiede
    0.90
    情報は
    0.88
    勤務
    0.87
     because
    0.87
     relazioni
    0.85
    razioni
    0.84
    Activations Density 0.001%

    No Known Activations