© 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. 2476
    Prev
    Next
    INDEX
    Explanations

    technical specifications or variable assignments

    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
    CallSettings
    0.72
    товых
    0.66
     Portman
    0.61
     thừa
    0.60
     ガラス
    0.59
    셨
    0.58
    全長
    0.58
    TS
    0.57
    제를
    0.57
     Bens
    0.57
    POSITIVE LOGITS
     মর
    0.56
    [`
    0.55
     live
    0.55
    rir
    0.55
     एकेडमी
    0.53
    ля
    0.53
    架
    0.53
     vapor
    0.53
     canceled
    0.53
     Α
    0.53
    Activations Density 0.348%

    No Known Activations