© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    Xbox One

    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
     ट्रीट
    0.72
    ieves
    0.69
    H
    0.69
    ivity
    0.68
     H
    0.67
     Hew
    0.66
    ective
    0.64
     අව
    0.64
    Hew
    0.64
    Ꮋ
    0.63
    POSITIVE LOGITS
    irken
    0.64
    indle
    0.63
    ferd
    0.61
    icznego
    0.59
    Permanent
    0.57
     කු
    0.57
    Internal
    0.55
     உள்ளட
    0.55
     সুষ্ঠ
    0.54
     Permanent
    0.54
    Activations Density 0.150%

    No Known Activations