© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66234
    Prev
    Next
    INDEX
    Explanations

    HLHS

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

    programming and code-related syntax elements like brackets, imports, variable names, and code formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     blé
    -1.13
    rógeno
    -1.07
    èses
    -1.00
     indígena
    -0.99
    utzen
    -0.98
     électroniques
    -0.98
     dessus
    -0.96
    怀里
    -0.96
    我国
    -0.95
     affich
    -0.94
    POSITIVE LOGITS
    ませんが
    0.98
     lusso
    0.94
    ませんでした
    0.94
    consider
    0.92
    总会
    0.91
    のですね
    0.90
     successivo
    0.89
     spezial
    0.88
     THINK
    0.86
     путем
    0.86
    Activations Density 0.197%

    No Known Activations