© 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. 54365
    Prev
    Next
    INDEX
    Explanations

    civilians and military honors

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

    The neuron consistently fires on multi‐digit numeric tokens (e.g. years, IDs, counts).

    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
     Hat
    -0.67
     hat
    -0.67
     Anger
    -0.63
     Tall
    -0.62
    habilit
    -0.62
    erre
    -0.61
    ⇧
    -0.61
     salad
    -0.61
     мой
    -0.61
    です
    -0.60
    POSITIVE LOGITS
    柾
    0.76
     動画
    0.74
     DCS
    0.71
     neurom
    0.71
     Sponge
    0.70
    Bigr
    0.70
     Koen
    0.69
    lievo
    0.68
     bóng
    0.68
     прика
    0.68
    Activations Density 0.054%

    No Known Activations