© 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. 78077
    Prev
    Next
    INDEX
    Explanations

    COUNT trigger analysis

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

    The neuron fires on numeric tokens or digit sequences (i.e., 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
    邈
    -0.77
     Quin
    -0.68
    EQUIPMENT
    -0.67
     кількість
    -0.63
    携
    -0.62
    泛
    -0.61
    ευ
    -0.61
     longitudinal
    -0.60
     Off
    -0.60
     Patrol
    -0.60
    POSITIVE LOGITS
    밌
    0.72
    ╜
    0.71
    autom
    0.69
    ១
    0.67
     spectator
    0.67
     Wilkins
    0.66
    datagrid
    0.66
    čky
    0.66
     survi
    0.65
    analyse
    0.64
    Activations Density 0.074%

    No Known Activations