© 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. 128989
    Prev
    Next
    INDEX
    Explanations

    Hamburg

    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
    '
    -3.00
    
    -2.56
    肯定是
    -2.44
    *
    -2.38
    y
    -2.36
    就算是
    -2.34
     unſ
    -2.34
    也只是
    -2.25
    ностью
    -2.22
    就不是
    -2.13
    POSITIVE LOGITS
    ᮣ
    2.47
    镚
    2.42
    ستارهای
    2.22
    襤
    2.19
    ⤙
    2.13
    ㌧
    2.11
    骉
    2.09
    ftet
    2.09
    ification
    2.08
    轫
    2.05
    Activations Density 0.002%

    No Known Activations