© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41877
    Prev
    Next
    INDEX
    Explanations

    nat and Monterey Bay

    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_16_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
    6
    1.13
    0
    1.10
    5
    1.05
    (
    1.02
    1
    1.00
    (\
    0.96
    ه
    0.94
    ים
    0.93
    ा
    0.89
    8
    0.87
    POSITIVE LOGITS
    nat
    0.89
    it
    0.85
    Nat
    0.79
    ar
    0.79
     सिटी
    0.79
     NAT
    0.77
    ن
    0.77
    ulously
    0.72
    ्टर
    0.72
    os
    0.71
    Activations Density 0.002%

    No Known Activations