© 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. 28720
    Prev
    Next
    INDEX
    Explanations

    personal data or specific numbers

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

    tf create map

    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
     ২০১৫
    0.80
     xrange
    0.77
     २०१
    0.73
     Huffington
    0.71
     Skype
    0.63
     ۲۰۱
    0.62
     AdWords
    0.61
    
    0.59
     Архів
    0.57
     AngularJS
    0.57
    POSITIVE LOGITS
     ২০২২
    1.30
    🫶
    1.27
    🥹
    1.20
    🫣
    1.11
    🫢
    1.10
    🫠
    1.09
     २०२२
    1.08
    🫡
    1.08
    🤍
    1.07
    🥲
    1.07
    Activations Density 0.000%

    No Known Activations