© 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. 63963
    Prev
    Next
    INDEX
    Explanations

    establishing a context

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

    communication evolving beyond lists

    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
     ncols
    0.43
    ل
    0.43
    جز
    0.42
    vern
    0.42
    不少
    0.42
    mandatory
    0.42
    ائز
    0.41
     Peaks
    0.40
    畅
    0.40
    plays
    0.39
    POSITIVE LOGITS
     отношении
    0.48
     інших
    0.48
     establishing
    0.47
     Сле
    0.45
     своём
    0.45
    荨
    0.45
     городе
    0.45
     міста
    0.45
    เลต
    0.45
     নিকটে
    0.44
    Activations Density 0.000%

    No Known Activations