© 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. 113170
    Prev
    Next
    INDEX
    Explanations

    code identifiers and keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    underscores in variable names, table names, and identifiers in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </td>
    -1.77
     will
    -1.73
     -
    -1.70
    </b>
    -1.70
    </th>
    -1.69
     $-$
    -1.57
     about
    -1.50
    Meski
    -1.49
     viaja
    -1.48
     For
    -1.46
    POSITIVE LOGITS
     quelconque
    1.52
    cómo
    1.44
    
    1.42
     フリル
    1.41
     Danemark
    1.41
    taient
    1.37
    姈
    1.37
     leſs
    1.35
     dinosaurio
    1.34
     usein
    1.34
    Activations Density 0.057%

    No Known Activations