© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    sensitive information, data, topics

    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
    </i>
    -2.53
     Näch
    -2.41
    gebras
    -2.39
    价格
    -2.38
     inept
    -2.33
    ┲
    -2.31
    ため
    -2.30
     linken
    -2.23
     anderen
    -2.22
    ﮕ
    -2.22
    POSITIVE LOGITS
    that
    3.20
     That
    2.91
    犇
    2.83
    轫
    2.70
    鋮
    2.56
    ୌ
    2.52
     способствует
    2.50
    𓄹
    2.50
    加熱
    2.42
     rằng
    2.34
    Activations Density 0.011%

    No Known Activations