© 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. 146380
    Prev
    Next
    INDEX
    Explanations

    Sanssouci, his work, rosewater

    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
     dry
    0.73
    ེ་
    0.70
     ফাইল
    0.70
     cush
    0.70
    囦
    0.69
     وإن
    0.68
    乙方
    0.68
     proceder
    0.68
    壺
    0.67
     symmetrical
    0.67
    POSITIVE LOGITS
     Bajaj
    0.82
    possessed
    0.76
    tober
    0.75
    point
    0.74
    fps
    0.69
    poetry
    0.69
    psc
    0.69
     нор
    0.68
    तीन
    0.67
    素敵
    0.66
    Activations Density 0.000%

    No Known Activations