© 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. 196408
    Prev
    Next
    INDEX
    Explanations

    places and activities

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

    stories, races, and numbers

    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
     zooming
    0.49
     지하
    0.46
    呑
    0.46
    멱
    0.46
     тар
    0.45
     darken
    0.45
     passcode
    0.45
     cách
    0.45
    過ぎ
    0.44
     Rajya
    0.44
    POSITIVE LOGITS
    histoire
    0.54
     வரலாறு
    0.51
    hingga
    0.45
    Functions
    0.45
    د
    0.45
    لوب
    0.44
    react
    0.44
    今天的
    0.44
    dyna
    0.43
    shooter
    0.43
    Activations Density 0.000%

    No Known Activations