© 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. 165512
    Prev
    Next
    INDEX
    Explanations

    hours, american, interact with

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

    handles user registration

    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
    scri
    0.52
    rier
    0.52
    astery
    0.49
    ly
    0.49
    itely
    0.47
    ри
    0.46
    riever
    0.45
    ۔
    0.45
     التاريخ
    0.44
    der
    0.44
    POSITIVE LOGITS
    ঁজ
    0.48
     akong
    0.47
     Maldives
    0.46
     můžete
    0.46
    ͌
    0.46
     Kyrgyz
    0.46
    ରା
    0.46
     ekstrem
    0.45
     samtidig
    0.45
     underway
    0.44
    Activations Density 0.000%

    No Known Activations