© 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. 99502
    Prev
    Next
    INDEX
    Explanations

    licenses followed by slash

    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
    F
    -2.44
    K
    -2.17
    M
    -2.11
    H
    -2.06
    V
    -2.06
    B
    -1.95
    N
    -1.93
     At
    -1.91
    P
    -1.88
     During
    -1.88
    POSITIVE LOGITS
    licenses
    2.34
    鶿
    2.31
    鱨
    2.19
     cocin
    2.17
     superbes
    2.14
     magnifiques
    2.00
    Spolja
    1.93
     écrans
    1.91
     殼
    1.88
     Siehe
    1.87
    Activations Density 0.036%

    No Known Activations