© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32895
    Prev
    Next
    INDEX
    Explanations

    list of itemsThese [number] speciesteams are

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

    The neuron fires on numeric data—particularly standalone numbers and measurements (e.g., counts, statistics, and decimal values).

    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
     “
    -1.09
    ᴠ
    -0.95
     such
    -0.94
    arschijnlijk
    -0.94
    としても
    -0.92
    如
    -0.90
    起源
    -0.90
     but
    -0.90
     cause
    -0.87
    厨房
    -0.86
    POSITIVE LOGITS
     derzeit
    1.12
    徐々に
    1.09
     who
    1.07
     块
    1.05
     presently
    1.05
     poszczegól
    1.04
     Tiếng
    1.01
    ってもら
    1.00
    clockwise
    1.00
     quienes
    1.00
    Activations Density 0.051%

    No Known Activations