© 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. 17581
    Prev
    Next
    INDEX
    Explanations

    during time

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

    how often skills occur

    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
     Ρ
    0.46
     πάντα
    0.46
    说什么
    0.45
     ആവശ
    0.45
     চাইলে
    0.43
     દેશ
    0.43
     แรก
    0.42
     л
    0.41
    нинг
    0.41
    αρ
    0.41
    POSITIVE LOGITS
     tijdens
    0.69
     occurring
    0.68
     occurred
    0.65
     ocur
    0.65
     durante
    0.64
     lors
    0.64
     occured
    0.63
     occuring
    0.63
     during
    0.61
     během
    0.61
    Activations Density 0.000%

    No Known Activations