© 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. 186789
    Prev
    Next
    INDEX
    Explanations

    under antit, OPS was, ratio ranks, situations easier

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

    adjectives describing length/state

    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
     xylem
    0.54
    ско
    0.51
     করিয়াছেন
    0.49
    ASX
    0.49
    ।
    0.49
     тока
    0.49
     ไหร่
    0.48
    oxyde
    0.48
     phasor
    0.47
    शुल्क
    0.47
    POSITIVE LOGITS
     كل
    0.57
    ቸው
    0.53
     ال
    0.51
    iendo
    0.50
     الفي
    0.50
    يرا
    0.48
     continu
    0.48
     إ
    0.47
     أج
    0.46
    iene
    0.46
    Activations Density 0.000%

    No Known Activations