© 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. 32206
    Prev
    Next
    INDEX
    Explanations

    diagnosis and classification

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

    software/technical terms related to diagnostics and classification systems.

    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
     Sumatera
    -0.85
     zeigte
    -0.75
    ㄦ
    -0.74
     despite
    -0.74
     rifles
    -0.73
     Ofrece
    -0.72
     들
    -0.72
    Ubi
    -0.70
    algebras
    -0.70
    ائق
    -0.69
    POSITIVE LOGITS
    描いて
    0.73
    Focused
    0.72
    ši
    0.72
     undi
    0.72
    stä
    0.71
    
    0.71
     Само
    0.71
    MultipartFile
    0.70
    resten
    0.69
     registrados
    0.68
    Activations Density 0.017%

    No Known Activations