Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1017
    Prev
    Next
    INDEX
    Explanations

    embassy or consulate

    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
    да
    0.98
    い
    0.95
    ל
    0.89
    ز
    0.88
    ený
    0.82
    ۰
    0.82
    ्यू
    0.81
     лидер
    0.81
    了一个
    0.79
    לה
    0.75
    POSITIVE LOGITS
    them
    1.01
     hydrogens
    1.01
    ﺗ
    0.99
    ouch
    0.94
    but
    0.94
     afar
    0.93
    representing
    0.93
    their
    0.93
    they
    0.93
    the
    0.92
    Activations Density 0.002%

    No Known Activations