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. 572
    Prev
    Next
    INDEX
    Explanations

    OpenAI or Stanley Kubrick

    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
    将
    2.42
     rupt
    2.22
    ه
    2.14
    ಿವೆ
    2.11
    ानु
    2.08
     panor
    2.08
    ют
    1.98
    هما
    1.98
     মাত্র
    1.95
     transcriptome
    1.92
    POSITIVE LOGITS
    ו
    2.56
    ח
    2.47
    om
    2.33
    י
    2.16
    ve
    1.98
    ga
    1.96
    withstanding
    1.95
    uk
    1.91
    mber
    1.90
    л
    1.89
    Activations Density 0.057%

    No Known Activations