© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13394
    Prev
    Next
    INDEX
    Explanations

    could use some

    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
    队的
    -1.68
     orgánico
    -1.66
     circumstances
    -1.56
    ptian
    -1.55
     chod
    -1.52
     Erwartungen
    -1.52
     BUT
    -1.50
     dangers
    -1.49
     remaining
    -1.49
    NSON
    -1.47
    POSITIVE LOGITS
    at
    1.55
     během
    1.42
    »,
    1.39
    芣
    1.36
     in
    1.30
    »;
    1.30
     */
    1.27
    を使
    1.25
    :
    1.25
    ів
    1.23
    Activations Density 0.011%

    No Known Activations