© 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. 59726
    Prev
    Next
    INDEX
    Explanations

    arrays, vectors, or lists initialized with curly braces

    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
    A
    -1.65
    in
    -1.63
    We
    -1.62
    <em>
    -1.61
     where
    -1.59
     it
    -1.52
    𖧧
    -1.45
    AS
    -1.43
    Your
    -1.40
    </em>
    -1.36
    POSITIVE LOGITS
    ⑊
    1.59
    ,*
    1.56
    glMatrix
    1.55
    Gibt
    1.54
     ними
    1.53
    ,..
    1.52
     prendere
    1.49
    ,​
    1.49
    einer
    1.48
    Nachteile
    1.48
    Activations Density 0.004%

    No Known Activations