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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3710
    Prev
    Next
    INDEX
    Explanations

    website section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    <h4>
    0.96
    Mostrar
    0.94
    <h1>
    0.93
    Reducing
    0.92
    Angular
    0.88
    Compile
    0.88
    Spray
    0.88
    <h3>
    0.88
    <h2>
    0.87
    Wenn
    0.86
    POSITIVE LOGITS
     already
    1.09
     need
    1.00
     customers
    0.98
     frequently
    0.95
     likely
    0.93
     recently
    0.90
     not
    0.86
     prescription
    0.85
     partners
    0.85
     ready
    0.83
    Activations Density 0.001%

    No Known Activations