© 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. 28683
    Prev
    Next
    INDEX
    Explanations

    years and countries

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

    years, dates, and specific events

    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
     Patreon
    0.49
    令和
    0.48
     Insta
    0.44
     ২০১৮
    0.44
     influencer
    0.44
     Realme
    0.44
     GitLab
    0.44
     بالع
    0.43
     章
    0.43
    POSITIVE LOGITS
     ২০১১
    0.62
     ২০১২
    0.62
    oul
    0.43
    http
    0.41
     http
    0.40
    ulz
    0.40
    Mitt
    0.39
     Mitt
    0.38
    ול
    0.38
    DK
    0.38
    Activations Density 0.136%

    No Known Activations