© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4251
    Prev
    Next
    INDEX
    Explanations

    fictional characters and popular media

    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
    女優
    0.70
     obscene
    0.66
     बसों
    0.65
     ರಾಷ್ಟ
    0.64
    窪
    0.64
    合い
    0.64
    opathie
    0.63
    椙
    0.63
    charts
    0.62
    <unused1835>
    0.62
    POSITIVE LOGITS
     Vegeta
    1.01
     Goku
    1.00
     Arag
    0.99
     Arya
    0.98
     Batman
    0.98
     Luffy
    0.96
     Eren
    0.96
     Luke
    0.96
     Zoro
    0.95
    olverine
    0.94
    Activations Density 0.136%

    No Known Activations