© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1331
    Prev
    Next
    INDEX
    Explanations

    La Flèche

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

    improvements and explanations

    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
     게
    0.38
     యు
    0.38
     यु
    0.35
     Shih
    0.34
     sinter
    0.34
     माली
    0.34
    凵
    0.34
     टे
    0.34
     ইউ
    0.33
     Kenneth
    0.32
    POSITIVE LOGITS
    FO
    0.43
     Bauer
    0.43
    Pav
    0.39
    asser
    0.39
    pav
    0.39
     Buster
    0.39
    Fo
    0.38
    Stamp
    0.38
    evol
    0.37
    YN
    0.37
    Activations Density 0.060%

    No Known Activations