© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    news headlines

    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
     schmerz
    -1.36
    ->$
    -1.20
     which
    -1.20
    老实
    -1.14
    xvii
    -1.10
    %";
    -1.10
     અને
    -1.09
    着一个
    -1.08
    WebElementEntity
    -1.07
     rời
    -1.06
    POSITIVE LOGITS
     others
    1.48
     become
    1.21
    1
    1.20
     их
    1.18
     such
    1.17
    猕
    1.12
    ﾅ
    1.12
    0
    1.11
    ፑ
    1.09
     is
    1.08
    Activations Density 0.055%

    No Known Activations