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. 1219
    Prev
    Next
    INDEX
    Explanations

    make or create

    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
     оса
    0.70
    mán
    0.64
    m
    0.62
    пло
    0.61
    تن
    0.60
     хотелось
    0.60
     거죠
    0.60
    يون
    0.59
    하
    0.59
    gable
    0.58
    POSITIVE LOGITS
    做一个
    0.85
     erstellen
    0.81
    ']])
    0.81
     Bolts
    0.81
    อป
    0.80
    jač
    0.80
     vara
    0.79
    estal
    0.78
    स
    0.78
    ότητα
    0.75
    Activations Density 0.003%

    No Known Activations