© 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. 79312
    Prev
    Next
    INDEX
    Explanations

    washing dishes, many more

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

    macrostate motif innings strategies

    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
    此同时
    0.49
    曖
    0.49
     Thal
    0.47
    虚
    0.45
    天皇
    0.45
    衽
    0.45
    吽
    0.44
     Gig
    0.43
    辍
    0.43
    惣
    0.43
    POSITIVE LOGITS
     ކ
    0.48
    ，
    0.48
    cc
    0.46
     m
    0.45
    änglich
    0.45
    araf
    0.44
    ।
    0.44
    ales
    0.43
    aid
    0.43
     ड
    0.43
    Activations Density 0.000%

    No Known Activations