© 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. 34-GEMMASCOPE-RES-131K
    7. 32750
    Prev
    Next
    INDEX
    Explanations

    domains, signatures, dna, questions

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

    technical elements in code or digital signatures, particularly looking for slashes, equals signs, and cryptographic components.

    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
     Civilian
    -0.81
     lyrics
    -0.78
     goog
    -0.77
    endela
    -0.77
     Schub
    -0.73
    涎
    -0.73
     Ewing
    -0.73
     référence
    -0.73
     buckling
    -0.73
    ogene
    -0.72
    POSITIVE LOGITS
    DOMAIN
    0.92
    EIP
    0.90
     domain
    0.87
    recover
    0.82
     схема
    0.77
     signing
    0.76
     recuperar
    0.73
    촌
    0.73
     cantora
    0.73
     signature
    0.72
    Activations Density 0.001%

    No Known Activations