© 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. 236769
    Prev
    Next
    INDEX
    Explanations

    related to tiles and accessories

    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
    ký
    0.51
    quả
    0.45
    évén
    0.44
    မှာ
    0.44
    времен
    0.43
     kör
    0.43
    (':
    0.43
     rév
    0.43
    kej
    0.42
    Emitter
    0.42
    POSITIVE LOGITS
     likes
    0.49
    גה
    0.47
    似
    0.46
    ීමට
    0.44
     Likes
    0.43
     onBackPressed
    0.42
    咿
    0.42
     Slowly
    0.41
    素敵な
    0.41
     doctrinal
    0.41
    Activations Density 0.001%

    No Known Activations