© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3356
    Prev
    Next
    INDEX
    Explanations

    in self or in words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     `${
    0.73
     $"{
    0.65
    `${
    0.65
    itemId
    0.64
     int
    0.64
    sprintf
    0.63
    parseInt
    0.63
    "{
    0.62
    intValue
    0.60
    int
    0.59
    POSITIVE LOGITS
     spectra
    0.68
     artistdata
    0.63
    ⵕ
    0.63
     corpi
    0.55
    ([...
    0.55
    ంచరీలు
    0.54
    আনুশকা
    0.53
     abiertas
    0.53
     estudia
    0.52
    acteria
    0.52
    Activations Density 0.004%

    No Known Activations