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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2693
    Prev
    Next
    INDEX
    Explanations

    oak look

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

    describing specific states or entities

    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
     Kakkar
    0.46
    竽
    0.45
     Kao
    0.42
     erythe
    0.41
     Hic
    0.41
     २४
    0.40
     Acting
    0.39
     ܥ
    0.39
     عفوا
    0.39
     maksymal
    0.39
    POSITIVE LOGITS
    plot
    0.49
     plot
    0.47
    Band
    0.42
    BIG
    0.42
    grip
    0.41
    deep
    0.41
    vo
    0.40
    so
    0.40
    cou
    0.40
    Gra
    0.40
    Activations Density 0.000%

    No Known Activations