© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48702
    Prev
    Next
    INDEX
    Explanations

    disruptive workflows, Electricity, lead generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ী
    0.53
    top
    0.46
    emergency
    0.46
    drunk
    0.45
     parenting
    0.44
     despair
    0.44
    ají
    0.43
     cyberpunk
    0.43
    cancel
    0.43
     tycker
    0.42
    POSITIVE LOGITS
     pharmaceuticals
    0.47
    >)`](
    0.44
     ঔষধ
    0.43
     nrows
    0.42
     Kenya
    0.41
    atios
    0.41
    觐
    0.40
     omin
    0.39
     Stairs
    0.39
    codiles
    0.39
    Activations Density 0.000%

    No Known Activations