© 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. 44246
    Prev
    Next
    INDEX
    Explanations

    names like Manning, Peyton, Manly

    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
     been
    -2.80
     dunklen
    -2.63
    늄
    -2.45
     Verhält
    -2.34
    rógeno
    -2.31
    ᥬ
    -2.28
     欣赏
    -2.28
     あります
    -2.23
     hermanas
    -2.23
     endeavors
    -2.22
    POSITIVE LOGITS
    <td>
    3.45
    踯
    2.84
    鸸
    2.73
    </td>
    2.69
    </sup>
    2.63
    趼
    2.59
    欵
    2.52
     koel
    2.50
    </h6>
    2.48
    蒌
    2.47
    Activations Density 0.004%

    No Known Activations