© 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-65K
    7. 36836
    Prev
    Next
    INDEX
    Explanations

    what is the capital

    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_65k_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
    Particles
    0.54
    ’
    0.49
     questionnaires
    0.46
    [*]
    0.45
     damned
    0.45
     aqueous
    0.44
    IOD
    0.44
    biggest
    0.44
    last
    0.44
     भाषा
    0.43
    POSITIVE LOGITS
    段
    0.47
    なた
    0.46
    زمت
    0.45
     realizzare
    0.45
    ังก์
    0.43
    均
    0.43
    ꒪
    0.43
     procede
    0.42
    另
    0.42
    制定
    0.42
    Activations Density 0.002%

    No Known Activations