© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245721
    Prev
    Next
    INDEX
    Explanations

    before October

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    amy
    0.48
    toluene
    0.45
    ?
    0.43
    amen
    0.42
    aat
    0.42
     Therapeutic
    0.42
     Occupational
    0.41
     Pharmaceutical
    0.41
    amps
    0.41
     면
    0.41
    POSITIVE LOGITS
     våra
    0.46
     mūsų
    0.46
     nazionali
    0.46
     måtte
    0.46
     модерни
    0.46
     deixou
    0.45
     svojim
    0.44
    組み立て
    0.44
     своими
    0.44
     dejó
    0.44
    Activations Density 0.000%

    No Known Activations