© 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. 111411
    Prev
    Next
    INDEX
    Explanations

    Bad Beat Jackpot

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

    Street Fighter

    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
    if
    0.50
    ٠
    0.46
     поз
    0.45
     मंत्री
    0.45
     crit
    0.45
    ть
    0.44
     ";
    0.44
    。
    0.44
    ifa
    0.43
     ")";
    0.43
    POSITIVE LOGITS
    espół
    0.50
    მასრულ
    0.47
    დაც
    0.46
    Einstellungen
    0.46
    CXX
    0.44
    dataset
    0.43
     microcos
    0.43
    stahl
    0.43
    స్కీ
    0.43
    압
    0.43
    Activations Density 0.001%

    No Known Activations