© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5966
    Prev
    Next
    INDEX
    Explanations

    verbs followed by objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ’’
    0.57
    د
    0.56
    c
    0.55
    l
    0.54
    まるで
    0.54
    od
    0.52
    oğlu
    0.52
    d
    0.51
    lığını
    0.50
    cina
    0.50
    POSITIVE LOGITS
    0.63
    ТИ
    0.59
    ographic
    0.56
    ИТ
    0.56
    åg
    0.56
    но
    0.55
    糁
    0.55
     dàng
    0.55
    사가
    0.55
     glimpses
    0.55
    Activations Density 0.387%

    No Known Activations