© 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. 7622
    Prev
    Next
    INDEX
    Explanations

    news announcements and dates

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

    AP news on Russia Ukraine war

    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
     controversial
    0.60
    “[
    0.59
    "[
    0.59
     "[
    0.58
    --“
    0.58
     Controvers
    0.58
     “[
    0.55
     reportedly
    0.52
     pled
    0.52
     fucked
    0.52
    POSITIVE LOGITS
    .___
    0.73
     ___
    0.69
    ___
    0.68
    AP
    0.68
     AP
    0.63
    एपी
    0.54
     ____
    0.52
    ____
    0.51
    Associated
    0.51
     ″
    0.51
    Activations Density 0.102%

    No Known Activations