© 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. 21134
    Prev
    Next
    INDEX
    Explanations

    to and from phrases

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

    from/to keywords

    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
    in
    0.76
    燎
    0.57
    c
    0.56
     চিকিৎসা
    0.55
    AN
    0.55
     frumo
    0.55
    睉
    0.54
     cliquez
    0.53
     kleines
    0.53
     reconocer
    0.52
    POSITIVE LOGITS
     (
    0.93
    '
    0.70
    、
    0.70
     \
    0.66
     was
    0.66
     -
    0.65
     –
    0.64
    ;
    0.63
    /
    0.62
    ・
    0.62
    Activations Density 0.009%

    No Known Activations