© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16080
    Prev
    Next
    INDEX
    Explanations

    yellow alarm

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

    lists, code, and instructions

    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_16k_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
    dirt
    0.46
    兄
    0.45
    xcschemes
    0.45
     ದಿನ
    0.44
    遽
    0.44
    깜
    0.44
    峠
    0.43
    VF
    0.43
     उजा
    0.43
    bitat
    0.43
    POSITIVE LOGITS
     Trinidad
    0.46
     Tern
    0.46
     Kartik
    0.45
     Hemsworth
    0.44
     Hillary
    0.44
    يري
    0.44
     Dec
    0.43
     Obama
    0.43
     Terry
    0.43
     Bollywood
    0.43
    Activations Density 0.001%

    No Known Activations