© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161647
    Prev
    Next
    INDEX
    Explanations

    final selection or report

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

    motivational magnitude limits

    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
    sharing
    0.49
     SHIPPING
    0.47
    浴
    0.47
     Udaipur
    0.47
     wrestling
    0.44
    िया
    0.44
    벧
    0.43
    Sharing
    0.43
    暴
    0.43
    道的
    0.42
    POSITIVE LOGITS
     tensión
    0.56
     límites
    0.53
     definitiva
    0.52
     młod
    0.49
     poziom
    0.49
     definitivo
    0.48
     dług
    0.48
     இறுதி
    0.48
     autént
    0.47
     extraordinaria
    0.46
    Activations Density 0.000%

    No Known Activations