© 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-65K
    7. 2827
    Prev
    Next
    INDEX
    Explanations

    please provide

    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_65k_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
     sky
    0.47
     extraordinaire
    0.46
     THEM
    0.46
    atic
    0.46
     them
    0.46
    /
    0.45
    They
    0.45
     us
    0.45
    Oh
    0.44
    ITS
    0.43
    POSITIVE LOGITS
     Proceed
    0.76
    <unused2148>
    0.74
     revising
    0.73
    苧
    0.72
    <unused749>
    0.72
     proceeding
    0.71
     гуляць
    0.68
     meminta
    0.68
     rostrum
    0.68
     رؤ
    0.67
    Activations Density 0.772%

    No Known Activations