© 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. 179703
    Prev
    Next
    INDEX
    Explanations

    healing times

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

    lists and structured text

    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
    یر
    0.60
    ؕ
    0.53
     измене
    0.51
    उच्च
    0.49
    một
    0.48
    ὡ
    0.48
    आत्म
    0.47
     această
    0.47
    ༦
    0.47
     една
    0.46
    POSITIVE LOGITS
     newsletter
    0.56
     audience
    0.54
     network
    0.52
     N
    0.51
     audiovisual
    0.51
     Festival
    0.50
     colloqu
    0.50
     incentivize
    0.50
     inherit
    0.49
     historically
    0.48
    Activations Density 0.001%

    No Known Activations