© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    before diving

    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
    ب
    2.42
     blistering
    1.84
    我对
    1.84
    لل
    1.82
     convert
    1.81
    きました
    1.81
    ৯
    1.80
    ächlich
    1.78
    мо
    1.76
    が生
    1.73
    POSITIVE LOGITS
     وبعد
    2.38
     وعند
    2.13
    ে
    2.13
     ruedas
    2.02
    ä
    1.99
    iella
    1.96
     numele
    1.95
    kings
    1.94
     étrang
    1.92
    ップ
    1.89
    Activations Density 0.038%

    No Known Activations