© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    could you tell me

    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
     ലഭ്യ
    0.97
     cabinetry
    0.91
    افيه
    0.89
     disponibilidade
    0.88
     mastect
    0.87
    嚀
    0.86
     percol
    0.83
     affords
    0.81
     meltdown
    0.79
    牴
    0.79
    POSITIVE LOGITS
     Zhao
    2.57
     Zhou
    2.55
     Jiang
    2.52
     Zhang
    2.51
     Xiao
    2.40
     Liu
    2.38
     Wang
    2.36
    Zhao
    2.33
    Zhang
    2.32
     Qin
    2.31
    Activations Density 0.229%

    No Known Activations