© 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. 198857
    Prev
    Next
    INDEX
    Explanations

    common clauses and pairings

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

    buttons, Track Information, bacterial gastroenteritis, Database Level, loss of, reduction

    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
    Negative Logits
     Inequal
    0.44
    Strategies
    0.41
    🧠
    0.41
    മം
    0.40
    รับ
    0.39
     oxidize
    0.39
    กี
    0.39
     구독
    0.39
     ప్రే
    0.38
     decompose
    0.38
    POSITIVE LOGITS
     incumb
    0.60
     pagine
    0.55
     πλη
    0.51
     thatched
    0.51
     events
    0.47
    [];
    0.47
     Sikkim
    0.47
     ballots
    0.47
     dudas
    0.46
     Rhodesia
    0.46
    Activations Density 0.001%

    No Known Activations