© 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. 144528
    Prev
    Next
    INDEX
    Explanations

    maxim lighting, money, Lover

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

    improved, corrected, suggested

    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
    д
    0.46
    widehat
    0.44
    かって
    0.44
     eigenstates
    0.43
    юд
    0.42
    かう
    0.42
    ਾਰੇ
    0.42
    няка
    0.42
    者の
    0.42
    isar
    0.41
    POSITIVE LOGITS
     verrà
    0.52
    桫
    0.48
     dni
    0.48
     debía
    0.46
    \%,
    0.46
     considerazione
    0.46
     GridPane
    0.46
     deberán
    0.46
     bezahlen
    0.46
     Το
    0.46
    Activations Density 0.000%

    No Known Activations