© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5455
    Prev
    Next
    INDEX
    Explanations

    package names and company identifiers

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

    I take

    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
    檜
    0.40
    Breakfast
    0.38
    桧
    0.37
     uphol
    0.37
     விஷ
    0.37
     සී
    0.36
     صور
    0.36
     breakfast
    0.36
    明け
    0.35
    findViewById
    0.34
    POSITIVE LOGITS
     javax
    0.41
     oops
    0.41
    하지만
    0.41
    ㅇ
    0.41
    Мі
    0.40
    esercizio
    0.38
     "$"
    0.38
    ?」
    0.38
     Hes
    0.38
    뀨
    0.38
    Activations Density 0.001%

    No Known Activations