© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7070
    Prev
    Next
    INDEX
    Explanations

    select or choose one option

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

    The neuron strongly fires on the word “points” (i.e. when the text shows item‐point allocations like “(1 2 points)”), so it’s detecting mentions of point values or scoring weights in instructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ذي
    0.56
     Datas
    0.55
    બંધ
    0.55
    explain
    0.52
    تهي
    0.52
    દે
    0.52
    kelig
    0.51
    ୈ
    0.50
    GH
    0.50
    合物
    0.50
    POSITIVE LOGITS
     hombre
    0.66
     ánimo
    0.64
    Vater
    0.59
     jogar
    0.58
     maravilloso
    0.58
     ruck
    0.57
     coluna
    0.57
     columns
    0.57
     disponíveis
    0.56
     каждая
    0.56
    Activations Density 0.003%

    No Known Activations