© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42874
    Prev
    Next
    INDEX
    Explanations

    function calls

    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
    鶺
    -1.91
     moule
    -1.78
     haine
    -1.77
     automne
    -1.74
     Jenis
    -1.70
     Luar
    -1.69
     Depor
    -1.67
     vode
    -1.66
     pravi
    -1.65
     vasi
    -1.65
    POSITIVE LOGITS
     was
    2.70
     
    2.66
     "
    2.23
     .
    2.08
    ↵
    2.06
    -
    2.03
    —
    2.02
     somewhat
    1.97
     It
    1.83
     usando
    1.81
    Activations Density 0.022%

    No Known Activations