© 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. 59599
    Prev
    Next
    INDEX
    Explanations

    Maybe set

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

    separation between concepts

    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
    ，
    0.42
     soi
    0.41
     there
    0.40
     aquilo
    0.39
     (\
    0.39
    专项
    0.38
    зова
    0.37
    ;
    0.37
    izio
    0.36
    ুজ
    0.36
    POSITIVE LOGITS
     አንዳንድ
    0.61
     Bankr
    0.52
     Prendre
    0.52
     विचारधारा
    0.49
    晧
    0.48
     هنگام
    0.48
    Ⲓ
    0.47
     विवाद
    0.47
     Misc
    0.47
     schwier
    0.46
    Activations Density 0.000%

    No Known Activations