© 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. 394
    Prev
    Next
    INDEX
    Explanations

    connection and fastening

    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
    çay
    0.52
    會有
    0.50
    霢
    0.48
     capitalise
    0.48
    偲
    0.47
    ंसारी
    0.47
    寯
    0.46
     underestimate
    0.46
    鵃
    0.46
    kungan
    0.46
    POSITIVE LOGITS
    and
    0.63
    ä
    0.60
     மற்றும்
    0.57
    ită
    0.55
    il
    0.55
    ites
    0.53
    ats
    0.52
    ї
    0.50
    ı
    0.48
    å
    0.48
    Activations Density 0.189%

    No Known Activations