© 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. 8019
    Prev
    Next
    INDEX
    Explanations

    their responses

    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
    ing
    0.50
    С
    0.48
    h
    0.47
    П
    0.47
    cemment
    0.47
    ه
    0.46
    oğlu
    0.45
    ed
    0.45
    e
    0.45
    o
    0.44
    POSITIVE LOGITS
     estejam
    0.51
     proponents
    0.50
     специалисты
    0.50
     trường
    0.49
     estão
    0.49
     باشد
    0.49
    nél
    0.49
    िटी
    0.49
     अधिकांश
    0.49
     postoji
    0.48
    Activations Density 0.515%

    No Known Activations