© 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. 59239
    Prev
    Next
    INDEX
    Explanations

    and sugar

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

    inline CSScurrently runningagency teamStanford students

    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
    i
    0.73
     i
    0.57
    id
    0.56
    ac
    0.55
    and
    0.51
     e
    0.49
    ff
    0.48
    hs
    0.48
    \
    0.48
     animal
    0.48
    POSITIVE LOGITS
    яти
    0.52
     चुकी
    0.51
    궬
    0.51
    வாத
    0.50
    龴
    0.50
    扨
    0.49
    通り
    0.48
    山の
    0.48
     සහිත
    0.48
    ോഷ്യ
    0.48
    Activations Density 0.000%

    No Known Activations