© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2365
    Prev
    Next
    INDEX
    Explanations

    describing entities numerically

    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_22_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
    の
    0.65
     Died
    0.63
    IN
    0.63
    ATTER
    0.62
    ারে
    0.61
    ALWAYS
    0.61
    常に
    0.60
    的
    0.60
     आटा
    0.59
     Always
    0.58
    POSITIVE LOGITS
    etzt
    0.77
    chauff
    0.74
    assadors
    0.73
     photocon
    0.71
    elh
    0.68
    corrh
    0.67
    oderma
    0.67
    ElementChild
    0.66
     Whitley
    0.66
     Haw
    0.65
    Activations Density 0.021%

    No Known Activations