© 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. 140078
    Prev
    Next
    INDEX
    Explanations

    offers, photos, fell, entire, hills, nurturing

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

    AI, monitoring, logging, submit, find

    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
    囩
    0.51
    वासीय
    0.47
    ອີ
    0.46
     সম্পত্তির
    0.45
    📶
    0.45
    妧
    0.45
     अडचणी
    0.44
     PROBLEMS
    0.44
     ATT
    0.44
     اط
    0.44
    POSITIVE LOGITS
    extract
    0.58
    n
    0.52
     debacle
    0.51
     neige
    0.46
    是
    0.45
    decode
    0.44
    は
    0.43
    startsWith
    0.42
    erd
    0.42
    Lateral
    0.42
    Activations Density 0.000%

    No Known Activations