© 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. 249581
    Prev
    Next
    INDEX
    Explanations

    location indicators

    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
    žia
    0.45
    트
    0.43
    伊
    0.43
     chim
    0.42
    ళ్లు
    0.42
    ೇಷ
    0.42
    łą
    0.42
    ття
    0.42
    ției
    0.41
     trắng
    0.41
    POSITIVE LOGITS
    wold
    0.50
     عام
    0.47
     lobby
    0.46
     lobbying
    0.45
     $=\
    0.44
     Etsy
    0.44
     Lobby
    0.43
     LinkedIn
    0.43
     अकाउंट
    0.43
     habitat
    0.42
    Activations Density 0.000%

    No Known Activations