© 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. 4878
    Prev
    Next
    INDEX
    Explanations

    war

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

    war or warfare

    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
     `:`,
    0.43
    ভারত
    0.40
     sorting
    0.38
     colon
    0.38
    ocoder
    0.38
    Adr
    0.38
     ogen
    0.38
     Flan
    0.37
     $*$-
    0.37
     Sorting
    0.37
    POSITIVE LOGITS
    riors
    0.89
    fares
    0.84
    fare
    0.81
    FARE
    0.79
     waged
    0.72
    ্ল্ড
    0.71
    torn
    0.70
    rior
    0.69
    farin
    0.69
     torn
    0.67
    Activations Density 0.028%

    No Known Activations