© 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. 36116
    Prev
    Next
    INDEX
    Explanations

    freshide

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

    code endings

    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
     लगाना
    0.43
     stør
    0.42
    ড়
    0.41
     云
    0.40
    associazione
    0.40
    MESSAGE
    0.40
     اہل
    0.40
     چاہتے
    0.40
    想要
    0.40
    روت
    0.40
    POSITIVE LOGITS
    ↵↵↵
    0.57
     beets
    0.54
    ↵↵
    0.52
     rejo
    0.50
     None
    0.50
    ↵↵↵↵
    0.48
    ↵↵↵↵↵
    0.47
     mush
    0.46
     pickle
    0.46
     Sich
    0.45
    Activations Density 0.000%

    No Known Activations