© 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. 33040
    Prev
    Next
    INDEX
    Explanations

    donations, support, or transactions

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

    punctuation and common phrases

    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
     Angular
    0.47
     Feuilles
    0.44
    ，
    0.43
    "));
    0.43
     slat
    0.41
     Pythagoras
    0.39
    銀座
    0.39
    滝
    0.39
    機種
    0.39
     Gogh
    0.38
    POSITIVE LOGITS
     स्टूडेंट
    0.47
     دعم
    0.47
     بک
    0.46
     രാഷ്ട്രീയ
    0.44
     разобраться
    0.44
     हाउस
    0.44
     بیل
    0.43
     कॉपी
    0.43
    ائها
    0.42
    kerja
    0.42
    Activations Density 0.000%

    No Known Activations