© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11346
    Prev
    Next
    INDEX
    Explanations

    code examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    ⑴
    0.95
     welchen
    0.88
    ⑩
    0.87
    문을
    0.87
    서를
    0.86
     furniture
    0.86
    百家乐
    0.85
    ંટણી
    0.85
    ⓪
    0.85
     اعداد
    0.85
    POSITIVE LOGITS
    Ver
    0.67
     and
    0.59
    Le
    0.59
    current
    0.59
    rel
    0.58
     ಹಿಂದ
    0.58
    ’
    0.57
    دل
    0.57
    legend
    0.57
    We
    0.57
    Activations Density 0.300%

    No Known Activations