© 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. 145844
    Prev
    Next
    INDEX
    Explanations

    formula api

    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
    ិក
    0.80
    Pré
    0.79
    ေသ
    0.78
    jn
    0.78
    찍
    0.77
     mLocation
    0.77
    Character
    0.74
    Edge
    0.73
    <unused1070>
    0.73
     tiện
    0.72
    POSITIVE LOGITS
     kula
    0.74
     amendments
    0.73
     সংশ
    0.71
     отец
    0.66
     MO
    0.65
     walls
    0.63
     muš
    0.62
    aporte
    0.62
     amended
    0.62
     MV
    0.62
    Activations Density 0.002%

    No Known Activations