© 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. 177326
    Prev
    Next
    INDEX
    Explanations

    musical performer or creator

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

    part of chariots

    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
    ціона
    0.54
    pubescens
    0.53
    ೀವ
    0.50
    ᱲ
    0.50
    ṟ
    0.49
    গিত
    0.48
    ithvi
    0.48
    ಿದ್ದೇನೆ
    0.47
    まさ
    0.47
    ಐ
    0.47
    POSITIVE LOGITS
     Karaoke
    0.53
     songwriter
    0.53
     divider
    0.51
     gage
    0.50
     singer
    0.49
    /
    0.49
     dim
    0.46
     debugger
    0.46
     musicales
    0.46
     singing
    0.46
    Activations Density 0.000%

    No Known Activations