© 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. 135228
    Prev
    Next
    INDEX
    Explanations

    places, status, markets

    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
     android
    0.43
     referenced
    0.42
     workout
    0.41
    e
    0.41
     matchup
    0.41
     completed
    0.40
    y
    0.40
     prø
    0.39
    fd
    0.39
     bandwagon
    0.39
    POSITIVE LOGITS
    缛
    0.47
    东京
    0.47
    مدينة
    0.46
     города
    0.45
    独特的
    0.45
     уника
    0.45
     ضروری
    0.44
     Museums
    0.43
     город
    0.42
    achella
    0.42
    Activations Density 0.005%

    No Known Activations