© 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. 3869
    Prev
    Next
    INDEX
    Explanations

    nuanced picture

    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
    ness
    0.82
    වා
    0.73
     reasonably
    0.71
    م
    0.71
    lma
    0.69
     absolute
    0.68
    liss
    0.67
    r
    0.66
     suppose
    0.66
    ز
    0.66
    POSITIVE LOGITS
    ccess
    1.28
    uuuu
    1.25
    arantee
    1.16
    profen
    1.13
    pload
    1.11
    cci
    1.08
    ploader
    1.05
    rology
    1.04
    ipment
    1.03
    rologist
    1.02
    Activations Density 0.145%

    No Known Activations