© 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. 74794
    Prev
    Next
    INDEX
    Explanations

    In" context

    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
     not
    -2.55
     in
    -2.36
     from
    -2.08
    "
    -2.08
     (
    -2.05
     with
    -2.03
     as
    -2.00
     -
    -1.95
     which
    -1.95
     on
    -1.89
    POSITIVE LOGITS
    縢
    2.48
    泐
    2.31
    specifically
    2.27
    懨
    2.08
    despite
    1.95
     raiſ
    1.91
     quintessential
    1.91
     momentous
    1.89
     sooo
    1.88
    釤
    1.88
    Activations Density 0.113%

    No Known Activations