© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6724
    Prev
    Next
    INDEX
    Explanations

    owned by, created by, tested by

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

    by phrases indicating origin

    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_53_width_65k_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
    টা
    0.44
    га
    0.43
    By
    0.41
    ला
    0.39
    ル
    0.39
    ല
    0.39
    дового
    0.39
    ють
    0.39
    ਲਾ
    0.38
    ম
    0.38
    POSITIVE LOGITS
     către
    0.74
     someone
    0.66
     humans
    0.66
     Communists
    0.59
     seseorang
    0.57
     Nazis
    0.57
     our
    0.56
     amateurs
    0.56
     monks
    0.55
    someone
    0.55
    Activations Density 0.179%

    No Known Activations