© 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. 62913
    Prev
    Next
    INDEX
    Explanations

    Eek! The Cat, Muscle fiber

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

    version numbers in technical documents or code 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
    นิ
    -0.74
    onden
    -0.72
    Designation
    -0.71
    ponder
    -0.69
     Verfügung
    -0.69
    针
    -0.68
    észet
    -0.68
     refused
    -0.67
     mackerel
    -0.67
    Nascimento
    -0.66
    POSITIVE LOGITS
    юре
    0.72
    LIVE
    0.69
     superiores
    0.69
    Archie
    0.68
     rect
    0.68
     vm
    0.68
    做事
    0.68
     Archie
    0.67
    lers
    0.66
     hud
    0.66
    Activations Density 0.053%

    No Known Activations