© 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. 38992
    Prev
    Next
    INDEX
    Explanations

    network concepts

    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
    Because
    -1.90
     щодо
    -1.82
    When
    -1.81
    Since
    -1.80
    That
    -1.68
    From
    -1.56
    As
    -1.55
    With
    -1.55
    At
    -1.52
    Let
    -1.52
    POSITIVE LOGITS
    (
    1.55
    慵
    1.35
     אותם
    1.30
    akyti
    1.28
     crossorigin
    1.28
    Voted
    1.27
    <bos>
    1.24
     nagu
    1.20
    を作り
    1.20
     '
    1.19
    Activations Density 0.058%

    No Known Activations