© 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. 119977
    Prev
    Next
    INDEX
    Explanations

    in comparison to

    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
    kitan
    -1.56
     It
    -1.51
     pintados
    -1.41
    рення
    -1.38
    chläge
    -1.34
    мія
    -1.33
     stoves
    -1.28
    räge
    -1.27
     origen
    -1.27
    liſh
    -1.27
    POSITIVE LOGITS
     a
    1.71
    炻
    1.44
    ates
    1.41
     -
    1.40
    );
    1.36
     there
    1.31
    我一
    1.31
     pokud
    1.30
    if
    1.30
     kuto
    1.29
    Activations Density 0.133%

    No Known Activations