© 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-65K
    7. 8283
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses and brackets

    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_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
    Practice
    0.79
    5
    0.75
    3
    0.73
    +(\
    0.73
    ф
    0.72
    по
    0.71
    :\/\/
    0.70
     perímetro
    0.69
    <\/
    0.69
    6
    0.69
    POSITIVE LOGITS
     deeply
    0.95
     tapestry
    0.85
     dissidents
    0.82
    eylon
    0.79
     bitterly
    0.79
     Democrats
    0.78
     Cors
    0.77
     researchers
    0.77
     partisan
    0.76
     ≈
    0.76
    Activations Density 0.011%

    No Known Activations