© 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. 239545
    Prev
    Next
    INDEX
    Explanations

    objects, people, and warnings

    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
     públic
    0.57
     음악
    0.56
     учеб
    0.53
     música
    0.51
    \}$,
    0.50
     função
    0.50
     enseñar
    0.50
    終於
    0.49
    들을
    0.49
    ."],
    0.49
    POSITIVE LOGITS
    la
    0.54
    r
    0.52
     avid
    0.49
    lar
    0.48
    卯
    0.48
     su
    0.48
     Il
    0.47
    lare
    0.47
    so
    0.46
     Consequences
    0.46
    Activations Density 0.000%

    No Known Activations