© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    Iona

    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
    s
    -4.78
    }
    -3.75
    ’
    -3.48
     This
    -3.38
    there
    -3.23
    b
    -2.94
    x
    -2.92
    的
    -2.73
    this
    -2.63
    www
    -2.63
    POSITIVE LOGITS
    ona
    2.81
    籮
    2.66
    ᠌
    2.56
    骉
    2.50
    ⩥
    2.41
    瓛
    2.38
    𓐍
    2.28
     poté
    2.28
    刳
    2.27
    等は
    2.22
    Activations Density 0.017%

    No Known Activations