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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1169
    Prev
    Next
    INDEX
    Explanations

    OpenAI models and API

    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
    ায়ণের
    1.66
    Nếu
    1.58
     whining
    1.58
    ات
    1.53
     leaching
    1.53
    暁
    1.50
    Heather
    1.48
    Prosecutors
    1.48
    gün
    1.48
    赟
    1.48
    POSITIVE LOGITS
    ו
    1.88
    ك
    1.64
    е
    1.61
    տր
    1.60
    ته
    1.59
    шие
    1.55
    ties
    1.55
    а
    1.55
    ن
    1.51
    て
    1.49
    Activations Density 0.029%

    No Known Activations