© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92695
    Prev
    Next
    INDEX
    Explanations

    code statements ending with semicolon

    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_34/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
    ),
    
    -1.06
    QUÉ
    -0.99
     prêtre
    -0.98
    𝗕
    -0.97
     Geschenk
    -0.96
    ніше
    -0.95
    tifie
    -0.95
     Luego
    -0.92
    \%,
    -0.92
    емости
    -0.91
    POSITIVE LOGITS
    ";}
    1.37
    ();}
    1.08
     could
    1.05
     or
    1.05
    </h1>
    1.05
     comuni
    1.02
    .
    1.00
    </h2>
    0.99
    </code>
    0.98
    ;}
    0.96
    Activations Density 0.019%

    No Known Activations