© 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-16K
    7. 3311
    Prev
    Next
    INDEX
    Explanations

    pure rice

    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_16k_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
     জাপান
    1.03
     Japón
    0.93
    yuan
    0.93
     Sakura
    0.90
     hongkong
    0.90
    🍜
    0.88
    Ки
    0.88
     Giappone
    0.87
    anime
    0.86
    Shanghai
    0.84
    POSITIVE LOGITS
     Utilization
    0.77
     pamphlet
    0.76
     Deter
    0.76
     Incidentally
    0.75
    Incidentally
    0.75
     caul
    0.74
     ※
    0.74
     Needless
    0.73
    첨
    0.72
     (=
    0.69
    Activations Density 0.092%

    No Known Activations