© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    taking out / removing

    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
    '
    -3.31
    {
    -2.69
    (
    -2.59
    他的
    -2.58
    "
    -2.53
    [
    -2.53
    e
    -2.52
    <b>
    -2.50
    an
    -2.44
    *
    -2.36
    POSITIVE LOGITS
     sabias
    2.39
     persino
    2.31
    嘖
    2.17
    飧
    2.09
    
    2.08
    啣
    2.08
    蘩
    2.03
    ⑉
    2.02
    玧
    2.02
    riezmann
    2.02
    Activations Density 0.006%

    No Known Activations