© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    code symbols and operators

    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>
    -2.34
    }$
    -2.20
    }{
    -2.02
    </sup>
    -1.87
    </h2>
    -1.74
     if
    -1.60
     However
    -1.59
    ↵↵↵↵↵↵↵↵↵↵
    -1.56
     a
    -1.55
    This
    -1.54
    POSITIVE LOGITS
     หรือ
    1.81
    audrait
    1.54
    ammans
    1.51
     maquilla
    1.49
    薗
    1.48
     atractivos
    1.47
    ⢇
    1.46
     halen
    1.45
     kleinere
    1.45
    tså
    1.45
    Activations Density 0.016%

    No Known Activations