© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    environmental fate model

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

    code formatting elements and numbers in programming code or technical documents.

    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
     SwitchCompat
    -0.79
     кухне
    -0.77
    Історія
    -0.72
    ölt
    -0.71
     Unidas
    -0.71
    ඛ
    -0.71
    Kä
    -0.71
    ások
    -0.70
     affirmé
    -0.69
    Ста
    -0.68
    POSITIVE LOGITS
    filenames
    0.74
     hashlib
    0.69
    kumar
    0.66
     proto
    0.66
    个性
    0.66
     تلویزیون
    0.66
     Ems
    0.66
    醇
    0.65
     Mudd
    0.65
     aeruginosa
    0.65
    Activations Density 0.034%

    No Known Activations