© 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. 38083
    Prev
    Next
    INDEX
    Explanations

    basic income

    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
    iles
    0.81
     doppia
    0.81
    òria
    0.80
    ه‌ای
    0.80
     wenden
    0.80
    ぅ
    0.78
    maria
    0.78
     idealized
    0.77
    metric
    0.77
    ີ
    0.77
    POSITIVE LOGITS
    Р
    0.93
    Ф
    0.90
    に限
    0.89
    М
    0.86
    Ра
    0.85
    О
    0.85
    НА
    0.84
     служит
    0.84
    смотря
    0.83
     рассказывает
    0.83
    Activations Density 0.000%

    No Known Activations