© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    special tokens, commands, URLs, venture, question, languages

    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
     unpacking
    0.63
     banana
    0.62
     unpack
    0.62
    izen
    0.61
     Banana
    0.60
    扫
    0.57
     रक्ष
    0.57
     unfiltered
    0.57
    ﾐ
    0.57
     scrapping
    0.56
    POSITIVE LOGITS
    parametric
    0.65
     उद्योग
    0.64
    ገባ
    0.62
     Ridg
    0.62
     param
    0.60
    ढ़
    0.59
     FRA
    0.59
    ঢ
    0.59
     যৌগ
    0.58
    staande
    0.58
    Activations Density 0.193%

    No Known Activations