© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39910
    Prev
    Next
    INDEX
    Explanations

    carmen and patti page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    -3.08
     —
    -2.84
    there
    -2.77
    in
    -2.66
    All
    -2.48
    just
    -2.47
    of
    -2.41
    —
    -2.38
    *
    -2.38
    &
    -2.36
    POSITIVE LOGITS
    麁
    3.14
    曏
    3.06
    蠑
    2.97
    镚
    2.88
     tetapi
    2.86
    肏
    2.83
     españ
    2.81
    ”?
    2.81
     Conſ
    2.80
    鷙
    2.80
    Activations Density 0.077%

    No Known Activations