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. 6354
    Prev
    Next
    INDEX
    Explanations

    great followed by a positive noun

    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
    I
    1.17
    <0x0D>
    1.09
    lastIndexOf
    1.09
    "{
    1.08
     NIV
    1.08
    \}$
    1.05
    apeti
    1.03
    casus
    1.02
    தாக
    1.01
     wiel
    1.01
    POSITIVE LOGITS
    ুর
    1.05
     slur
    1.05
    یک
    0.98
     Brace
    0.96
    о
    0.96
    一带
    0.96
    ó
    0.96
     डॉक्टर
    0.94
     таки
    0.94
    芏
    0.94
    Activations Density 0.008%

    No Known Activations