© 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. 11628
    Prev
    Next
    INDEX
    Explanations

    non-English characters and technical words

    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
     to
    0.70
    ०
    0.48
     veoma
    0.45
    ς
    0.45
    ը
    0.44
    ER
    0.42
     disa
    0.41
    して
    0.40
    то
    0.40
     numai
    0.40
    POSITIVE LOGITS
    ties
    0.64
     እና
    0.57
    al
    0.55
    g
    0.55
    v
    0.53
     जैसे
    0.52
    h
    0.50
    can
    0.50
     ಮತ್ತು
    0.46
    <unused416>
    0.45
    Activations Density 0.077%

    No Known Activations