© 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. 129268
    Prev
    Next
    INDEX
    Explanations

    numbers with following characters

    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
     Such
    -2.81
    i
    -2.38
    Such
    -2.25
    us
    -2.16
     "}";
    -2.14
    檮
    -2.11
    &
    -2.05
     the
    -2.02
     Absolutely
    -2.02
     These
    -2.00
    POSITIVE LOGITS
    1
    3.27
    ↵
    3.00
    潆
    2.75
    眛
    2.73
    咵
    2.52
    ſſen
    2.31
    dámské
    2.28
    哙
    2.25
    ሖ
    2.25
    🧌
    2.22
    Activations Density 0.017%

    No Known Activations