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. 3351
    Prev
    Next
    INDEX
    Explanations

    HTML section headers

    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
    螂
    0.75
    Bechyné
    0.74
    াইলেন
    0.72
    ваны
    0.71
    絖
    0.70
    Чу
    0.69
    ወሰ
    0.68
    挛
    0.68
    ታት
    0.67
    রামর্শ
    0.67
    POSITIVE LOGITS
    .]
    0.72
    </h3>
    0.69
     ві
    0.62
     literally
    0.60
     artifacts
    0.60
    <h3>
    0.60
     cloth
    0.60
     sculpture
    0.59
     fish
    0.59
     equates
    0.59
    Activations Density 0.001%

    No Known Activations