© 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. 34-GEMMASCOPE-RES-131K
    7. 117414
    Prev
    Next
    INDEX
    Explanations

    pain relief, osteogenic

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

    code or programming-related content, particularly import statements and package declarations in Java files.

    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_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
     even
    -0.89
    錚
    -0.85
    oplast
    -0.84
    тол
    -0.84
     just
    -0.82
    镯
    -0.81
     UserProfile
    -0.76
    '):
    -0.74
    мель
    -0.74
     may
    -0.73
    POSITIVE LOGITS
    ymce
    0.93
     ino
    0.86
     Mapper
    0.85
     магазина
    0.85
    Thy
    0.84
     marketed
    0.83
    ző
    0.83
    Transactional
    0.82
     tb
    0.81
     Integer
    0.80
    Activations Density 0.003%

    No Known Activations