© 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. 40722
    Prev
    Next
    INDEX
    Explanations

    time stamps

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

    secure transactions

    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
    ۔
    0.52
     Schrift
    0.48
    Chúng
    0.47
     abbiamo
    0.46
     comprehend
    0.46
     anlaş
    0.45
     ಮಾಹಿತ
    0.44
     Chúng
    0.44
     সিনেমা
    0.44
    筥
    0.44
    POSITIVE LOGITS
    implies
    0.49
    fixed
    0.47
     mowing
    0.47
    compensated
    0.47
     fixed
    0.46
    levels
    0.45
     cloves
    0.45
     sawing
    0.45
    comes
    0.44
     knee
    0.44
    Activations Density 0.000%

    No Known Activations