© 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. 188445
    Prev
    Next
    INDEX
    Explanations

    places and types of things

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

    creative text, json array, and programming

    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
    Lotus
    0.57
    的
    0.54
    建成
    0.54
     banner
    0.53
     Ghost
    0.53
    Ghost
    0.53
    Bird
    0.52
    MING
    0.51
     ghost
    0.51
    Reform
    0.50
    POSITIVE LOGITS
    inst
    0.50
    instances
    0.48
    ма
    0.47
    treated
    0.46
     デザイン
    0.46
    ಕ
    0.45
     ಅವು
    0.45
     ಸುರ
    0.45
    insulated
    0.44
    calls
    0.44
    Activations Density 0.000%

    No Known Activations