© 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. 240264
    Prev
    Next
    INDEX
    Explanations

    wiring diagram niche

    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
    ور
    0.54
     or
    0.51
    و
    0.49
     अणु
    0.49
     Suffering
    0.47
     Dodgers
    0.47
     Guns
    0.47
     baseball
    0.46
     Exhibit
    0.45
     zucchero
    0.45
    POSITIVE LOGITS
    closes
    0.51
    gaia
    0.51
    stery
    0.50
    medieval
    0.50
    bell
    0.49
    。
    0.48
    starttime
    0.47
    fler
    0.47
    ત્મ
    0.47
    kezi
    0.46
    Activations Density 0.001%

    No Known Activations