© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147131
    Prev
    Next
    INDEX
    Explanations

    official identification document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ่อ
    0.80
    ອີ
    0.73
     გახ
    0.73
     GRI
    0.73
    Diffuse
    0.72
    ﻏ
    0.71
     ол
    0.70
    ❂
    0.70
     IEquatable
    0.69
     கிஷ
    0.69
    POSITIVE LOGITS
     topped
    0.73
     arithmetic
    0.70
    top
    0.69
     effected
    0.69
     Spitzen
    0.68
     Regen
    0.65
    ρέ
    0.65
     habría
    0.64
     hypersurfaces
    0.64
     sweat
    0.64
    Activations Density 0.002%

    No Known Activations