© 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. 30417
    Prev
    Next
    INDEX
    Explanations

    Materials and methods

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

    The neuron detects section headings related to research methodologies, particularly "Materials and methods" sections in scientific papers.

    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
     компа
    -0.79
    Features
    -0.78
    ButterKnife
    -0.77
     construction
    -0.74
    ود
    -0.73
    notes
    -0.73
     occhiali
    -0.72
    كونات
    -0.71
     options
    -0.70
    스
    -0.70
    POSITIVE LOGITS
     *>(
    0.82
     Europäischen
    0.78
    copal
    0.73
     pearly
    0.72
     gezogen
    0.72
    ጭ
    0.72
     soiled
    0.71
    laan
    0.71
    modelName
    0.68
     Melrose
    0.68
    Activations Density 0.060%

    No Known Activations