© 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. 38709
    Prev
    Next
    INDEX
    Explanations

    breathe life into

    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
     commonly
    -1.60
     vents
    -1.52
    vantaged
    -1.47
     we
    -1.46
     one
    -1.43
    ibration
    -1.42
     liberación
    -1.39
     restauración
    -1.38
     hicieron
    -1.38
    𝘯
    -1.37
    POSITIVE LOGITS
     =
    1.54
    }
    1.52
    </b>
    1.44
    quiao
    1.33
     Fifty
    1.33
    கா
    1.32
    ),
    1.30
     breathed
    1.30
     denselben
    1.29
    ."
    1.28
    Activations Density 0.009%

    No Known Activations