© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133076
    Prev
    Next
    INDEX
    Explanations

    syrian army, american girl, candies

    np_acts-logits-general · gemini-2.5-flash-lite

    Mint Lemonade, reasoned response, critique of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Instagram
    0.41
     ​​
    0.39
     Rey
    0.38
     minister
    0.37
     मायने
    0.37
     YouTuber
    0.36
     Apps
    0.36
     more
    0.36
     Raya
    0.35
     Pavlov
    0.35
    POSITIVE LOGITS
    ໕
    0.52
     anex
    0.46
    gll
    0.46
     होतं
    0.44
    oretic
    0.43
    بري
    0.43
    үнд
    0.43
    벧
    0.43
    tenth
    0.42
    powiedz
    0.42
    Activations Density 0.000%

    No Known Activations