© 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. 216126
    Prev
    Next
    INDEX
    Explanations

    dig in, TS Association, signed by

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

    a definition or explanation

    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
     Allgemeine
    0.44
     Zellen
    0.43
     signalled
    0.43
     mains
    0.43
    ز
    0.43
     CPUs
    0.42
     LEDs
    0.42
     soya
    0.41
     ziel
    0.41
     aktive
    0.41
    POSITIVE LOGITS
     여기까지
    0.52
    ."'
    0.51
     पचा
    0.50
     саме
    0.49
     思っ
    0.48
     αυτή
    0.47
    akkha
    0.47
    ,":
    0.46
     ネックレス
    0.46
    ricane
    0.46
    Activations Density 0.000%

    No Known Activations