© 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. 13696
    Prev
    Next
    INDEX
    Explanations

    creating own things

    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
     \
    -3.55
    What
    -3.42
    0
    -3.06
    ”
    -2.92
    ”,
    -2.89
    Of
    -2.70
    >
    -2.67
    B
    -2.63
    by
    -2.59
    How
    -2.59
    POSITIVE LOGITS
    蕷
    2.81
    纐
    2.53
     we
    2.48
    褙
    2.47
    ῞
    2.47
    儇
    2.45
    懌
    2.45
     impec
    2.44
    .~\
    2.42
    —.
    2.42
    Activations Density 0.007%

    No Known Activations