© 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. 184016
    Prev
    Next
    INDEX
    Explanations

    available and others

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

    setting pygame display caption

    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
    ="|
    0.50
    Thinking
    0.49
    Plan
    0.49
    PLAN
    0.48
    NIS
    0.47
    慘
    0.47
    يدا
    0.46
    Tutorial
    0.46
    Sydney
    0.46
    Warnings
    0.46
    POSITIVE LOGITS
     અથવા
    0.51
     культура
    0.50
     MODKEY
    0.49
    nan
    0.48
     octagon
    0.48
     आए
    0.47
     있
    0.47
     одном
    0.47
     Ohr
    0.47
     outcrop
    0.47
    Activations Density 0.000%

    No Known Activations