© 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. 68518
    Prev
    Next
    INDEX
    Explanations

    published on dates

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

    languages, networks, branching

    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
     ንጥረ
    0.50
     паке
    0.46
     scan
    0.45
    𒄩
    0.45
     津
    0.45
     cyclone
    0.44
    মতী
    0.44
     chiến
    0.44
     bing
    0.44
    InCategory
    0.44
    POSITIVE LOGITS
    Y
    0.53
     Challenges
    0.47
    Q
    0.46
    ADE
    0.45
     Wisdom
    0.45
    Chars
    0.44
    Η
    0.44
     ingles
    0.43
    ISES
    0.43
     Metrics
    0.42
    Activations Density 0.001%

    No Known Activations