© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124644
    Prev
    Next
    INDEX
    Explanations

    constructor parameters or default values

    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
    涐
    -2.64
    <bos>
    -2.09
    readFileSync
    -1.98
     encargado
    -1.96
    chengladbach
    -1.91
    était
    -1.91
    ⁛
    -1.91
    ;
    -1.90
    scaleY
    -1.90
    濱
    -1.88
    POSITIVE LOGITS
     increasingly
    2.23
    te
    2.17
    …
    2.00
    “
    1.96
     Including
    1.95
    奩
    1.95
    —
    1.92
    2
    1.91
    g
    1.90
    a
    1.88
    Activations Density 0.009%

    No Known Activations