© 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. 16-GEMMASCOPE-2-RES-16K
    7. 6
    Prev
    Next
    INDEX
    Explanations

    listing parts

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

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_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
    驍
    0.63
    ្នែក
    0.61
    ುತ್ತೇನೆ
    0.58
    臻
    0.57
     jouw
    0.56
    殄
    0.56
    任何
    0.55
    もっと
    0.55
    ለያዩ
    0.55
    로
    0.55
    POSITIVE LOGITS
    ová
    0.71
    ica
    0.63
    ;
    0.63
    G
    0.60
    ock
    0.60
    a
    0.59
    h
    0.59
    es
    0.58
    ında
    0.57
     большой
    0.57
    Activations Density 0.000%

    No Known Activations