© 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. 191629
    Prev
    Next
    INDEX
    Explanations

    new directions

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

    labels, extensive information

    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
    ":{"
    0.50
     RSI
    0.49
     od
    0.48
     Div
    0.47
     ov
    0.47
     sua
    0.47
     MMM
    0.47
    emis
    0.46
     KE
    0.45
     ROS
    0.45
    POSITIVE LOGITS
    кой
    0.49
    फ्टर
    0.47
    फ्टी
    0.46
    ığında
    0.46
     अपनाने
    0.46
    ﻚ
    0.46
     руку
    0.45
     simulations
    0.44
    売り
    0.44
    ನ್ನು
    0.44
    Activations Density 0.000%

    No Known Activations