Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 141926
    Prev
    Next
    INDEX
    Explanations

    subnet IDs

    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
    ın
    0.61
    ри
    0.60
    на
    0.59
    a
    0.59
    na
    0.59
    '
    0.59
    dur
    0.54
     lodged
    0.52
    we
    0.52
    та
    0.50
    POSITIVE LOGITS
    ലൈ
    0.61
     lenguaje
    0.60
     प्रिंस
    0.60
    रह
    0.57
     電力
    0.56
    ᓘ
    0.55
     eighties
    0.55
     仕事
    0.55
    แพทย์
    0.54
    moto
    0.54
    Activations Density 0.001%

    No Known Activations