© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 991
    Prev
    Next
    INDEX
    Explanations

    of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ኃ
    0.68
     fac
    0.60
     শুটিং
    0.57
     मंत्र
    0.57
    kran
    0.56
     runtime
    0.55
    Careers
    0.55
    fac
    0.55
     career
    0.54
    face
    0.54
    POSITIVE LOGITS
     acquies
    0.63
     আব্দুর
    0.59
    μον
    0.58
     Mode
    0.58
    赴
    0.58
    擇
    0.57
     Ret
    0.55
     பிரி
    0.55
    অভি
    0.55
    toned
    0.55
    Activations Density 0.196%

    No Known Activations