© 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. 129116
    Prev
    Next
    INDEX
    Explanations

    election wins

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

    Symbols, deeds, designed, webs

    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
    (*
    0.50
    .(
    0.48
    *(
    0.48
     mbr
    0.47
    (
    0.47
    -(
    0.46
     uncertain
    0.46
    ((
    0.45
    Χ
    0.45
     concatenated
    0.44
    POSITIVE LOGITS
     السود
    0.51
    വിധ
    0.46
     ਹੀ
    0.46
     બી
    0.44
     гі
    0.44
     ವಿದ್ಯ
    0.44
    attaque
    0.44
     Джу
    0.44
    講的是
    0.44
    荊
    0.43
    Activations Density 0.000%

    No Known Activations