© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15826
    Prev
    Next
    INDEX
    Explanations

    geopolitical instability and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.58
    Path
    0.51
    ;
    0.48
    Type
    0.46
    In
    0.46
    Mitsubishi
    0.44
    path
    0.44
    l
    0.43
     Fortune
    0.43
     In
    0.43
    POSITIVE LOGITS
     preservar
    0.51
     সম্পূর্ন
    0.48
     dividir
    0.47
     mendatang
    0.46
    LIK
    0.46
    െന്നാണ്
    0.46
     ডু
    0.46
     correcto
    0.45
    婍
    0.45
     эл
    0.45
    Activations Density 0.013%

    No Known Activations