© 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. 88972
    Prev
    Next
    INDEX
    Explanations

    Serious Threat, Fan Mode, warranty eliminates

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

    match

    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
    دا
    0.54
     بول
    0.52
     تار
    0.51
     Lobster
    0.48
     ứng
    0.48
     متر
    0.47
     Administrative
    0.46
    [(
    0.45
    我们也
    0.44
     UBS
    0.44
    POSITIVE LOGITS
    apabb
    0.53
     TRANSPORTURI
    0.51
    authentic
    0.49
    ्यान
    0.45
    andang
    0.45
    ๎
    0.44
    ುತ್ತೇನೆ
    0.44
    ARCHITECTURE
    0.43
     kekurangan
    0.43
    ーフ
    0.43
    Activations Density 0.000%

    No Known Activations