© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 209744
    Prev
    Next
    INDEX
    Explanations

    essay, daily

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

    trivia nights

    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
    </em>
    0.45
     Philly
    0.45
     kasar
    0.45
    ัน
    0.43
     speeds
    0.43
    atok
    0.43
    ำ
    0.43
    ̉
    0.43
    리
    0.42
    ิน
    0.42
    POSITIVE LOGITS
     ইউনাই
    0.56
    dSample
    0.55
    CreateWall
    0.54
    Suggested
    0.53
    Caracter
    0.48
    Telephone
    0.48
    Buildable
    0.47
     podstawie
    0.47
     حالة
    0.46
    STANDARD
    0.46
    Activations Density 0.000%

    No Known Activations