© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    function arguments

    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
    </h4>
    -1.96
    at
    -1.75
     neues
    -1.74
    );
    -1.65
     He
    -1.63
    瞠
    -1.61
    3
    -1.59
     `
    -1.54
    et
    -1.53
    }$
    -1.53
    POSITIVE LOGITS
     of
    2.16
    𐐪
    2.14
     signifikan
    2.09
    伋
    2.03
    ötz
    1.91
     requesting
    1.89
     this
    1.79
    莚
    1.74
    顼
    1.74
    ൎ
    1.73
    Activations Density 0.001%

    No Known Activations