© 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. 101210
    Prev
    Next
    INDEX
    Explanations

    DearSir

    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
     uniquement
    -1.53
    alım
    -1.47
    Other
    -1.44
    Also
    -1.41
    quée
    -1.37
    ní
    -1.34
    极其
    -1.33
    ğiniz
    -1.33
    Our
    -1.31
     lutter
    -1.29
    POSITIVE LOGITS
     a
    1.98
     comenta
    1.63
     from
    1.47
     their
    1.46
    </strong>
    1.45
    /"+
    1.44
    ляции
    1.44
     that
    1.42
    可以在
    1.42
     andare
    1.41
    Activations Density 0.003%

    No Known Activations