© 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. 1957
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and operations

    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
     письмен
    0.76
     but
    0.71
     sent
    0.69
     proudly
    0.68
    ուն
    0.67
    ,
    0.66
     champion
    0.65
     scol
    0.64
     reigning
    0.64
    ">→</
    0.63
    POSITIVE LOGITS
     (((
    1.57
    ((
    1.56
     ((
    1.55
    ,(((
    1.53
    -[(
    1.49
    (((
    1.48
     $((
    1.46
     [(
    1.44
     √(
    1.44
    *((
    1.43
    Activations Density 0.485%

    No Known Activations