© 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. 188422
    Prev
    Next
    INDEX
    Explanations

    Ralphi

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

    depending on

    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
    宀
    0.43
    家用
    0.42
     Cit
    0.41
     ERISA
    0.41
     ilmiah
    0.40
     fondamental
    0.39
     enunci
    0.39
     Melon
    0.39
     Kep
    0.38
    <0x80>
    0.38
    POSITIVE LOGITS
    RAL
    0.50
    raient
    0.49
    ʀ
    0.47
    രക്ഷ
    0.46
    ']));
    0.46
    ருங்கள்
    0.46
    RAchievement
    0.45
     करिएगा
    0.45
    LON
    0.45
    ران
    0.45
    Activations Density 0.001%

    No Known Activations