© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11002
    Prev
    Next
    INDEX
    Explanations

    medical and descriptive terms

    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_9_width_262k_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
    此之外
    1.89
    تج
    1.74
     effecting
    1.63
    teile
    1.55
    ிய
    1.52
    '%
    1.50
    ން
    1.50
     फेव
    1.48
    ছেন
    1.47
    는
    1.46
    POSITIVE LOGITS
     escorted
    1.88
     TGF
    1.80
     Equipo
    1.74
     lysine
    1.72
     selam
    1.71
     bathed
    1.71
    Οι
    1.69
    eri
    1.67
     elytra
    1.66
     staggering
    1.64
    Activations Density 0.002%

    No Known Activations