© 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. 50721
    Prev
    Next
    INDEX
    Explanations

    distribute power, data, or resources

    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
    رو
    0.75
     ఎంత
    0.68
    apanicola
    0.66
     penthouse
    0.64
    У
    0.63
     socialize
    0.61
    ని
    0.60
     kleiner
    0.60
     descuento
    0.60
     ١
    0.59
    POSITIVE LOGITS
     Distribution
    1.13
     распреде
    1.09
     distributed
    1.08
     distributing
    1.08
     distributes
    1.03
     distribusi
    1.03
     distribution
    1.00
     distribu
    0.98
     বিতরণ
    0.98
    分布
    0.96
    Activations Density 0.024%

    No Known Activations