© 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. 107063
    Prev
    Next
    INDEX
    Explanations

    followed by continuation

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

    calculations and code cells

    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
     in
    0.54
    tt
    0.52
     dealers
    0.51
     Astros
    0.51
    k
    0.51
     stocks
    0.50
     investors
    0.49
    也
    0.49
    警
    0.48
     regressions
    0.48
    POSITIVE LOGITS
     рецеп
    0.54
     τρόπο
    0.52
    ")}}
    0.52
     உல
    0.51
    ónicas
    0.51
     வாழைப்பழ
    0.51
     ҷ
    0.51
     церков
    0.51
     کارت
    0.50
     کودک
    0.49
    Activations Density 0.000%

    No Known Activations