© 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. 43251
    Prev
    Next
    INDEX
    Explanations

    assistance, artificial, conditioning

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

    activities and processes

    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
    切
    0.49
     Cint
    0.48
    Questa
    0.47
     +#+
    0.46
    禮
    0.46
    媝
    0.44
    donut
    0.44
     這個
    0.44
     santa
    0.44
     πισ
    0.43
    POSITIVE LOGITS
     деятельности
    0.43
     의견
    0.42
     была
    0.41
    ிருந்தார்
    0.41
     പ്രവർത്തന
    0.40
     был
    0.40
     있었
    0.39
    contribution
    0.38
    ꯤ
    0.38
     использова
    0.38
    Activations Density 0.000%

    No Known Activations