© 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. 138284
    Prev
    Next
    INDEX
    Explanations

    react component imports

    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
     études
    0.57
     депозит
    0.55
     порядку
    0.55
     людини
    0.54
     ورځې
    0.54
     алгорит
    0.54
    嗕
    0.53
     alleles
    0.53
     випадку
    0.52
     entend
    0.52
    POSITIVE LOGITS
    ش
    0.55
    od
    0.53
    ید
    0.52
    id
    0.51
    c
    0.50
     Kep
    0.50
     Forestry
    0.49
    n
    0.49
    ن
    0.49
    is
    0.49
    Activations Density 0.003%

    No Known Activations