© 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. 146319
    Prev
    Next
    INDEX
    Explanations

    HTTP requests (GET, POST)

    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
     形
    0.90
    னா
    0.86
     unfore
    0.86
     Berg
    0.85
    któ
    0.84
    繁
    0.83
     кому
    0.83
     Bus
    0.82
     postup
    0.82
     Cristiano
    0.82
    POSITIVE LOGITS
    Updating
    0.83
     aldığı
    0.78
     শিশ
    0.73
    includegraphics
    0.72
    ดำเนิน
    0.70
    DF
    0.69
    "]);
    0.68
    Chord
    0.67
    Winning
    0.67
    (",");
    0.65
    Activations Density 0.001%

    No Known Activations