© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139030
    Prev
    Next
    INDEX
    Explanations

    offer, overseas, ancestor, artwork, opera, help

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

    analyze, standardize, work, quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    you
    0.49
     nakon
    0.45
    ...(
    0.43
    と
    0.43
    at
    0.42
    rated
    0.41
    pc
    0.41
    inois
    0.41
    sdk
    0.41
    ants
    0.41
    POSITIVE LOGITS
    Ẓ
    0.49
     levens
    0.47
     monoc
    0.46
     universal
    0.45
     enzyme
    0.45
     खोज
    0.43
     fungal
    0.43
     abundant
    0.43
     pensamento
    0.42
     alchemy
    0.41
    Activations Density 0.001%

    No Known Activations