© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66453
    Prev
    Next
    INDEX
    Explanations

    common word endings

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

    topics and their common follow-ups

    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
    ת
    0.47
    م
    0.47
     עבור
    0.46
    Л
    0.46
     edhe
    0.45
    ד
    0.44
    ל
    0.44
    ن
    0.43
    Этот
    0.42
     ايضا
    0.42
    POSITIVE LOGITS
    ,
    0.44
     Civil
    0.38
     corporations
    0.37
     życia
    0.37
     academies
    0.37
    -,
    0.36
     Organize
    0.36
     insanların
    0.35
     stakeholders
    0.35
     and
    0.34
    Activations Density 0.165%

    No Known Activations