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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 371
    Prev
    Next
    INDEX
    Explanations

    with categories, regard, respect, emphasis

    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_16k_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
    Y
    0.70
    Я
    0.69
    /*
    0.67
    It
    0.67
    Since
    0.63
    H
    0.62
    '{
    0.62
    etc
    0.62
    CH
    0.59
    Ε
    0.58
    POSITIVE LOGITS
     regard
    1.62
     regards
    1.62
     impunity
    1.38
    standing
    1.22
     respect
    1.18
    drawn
    1.17
     respecto
    1.13
     whom
    1.11
     emphasis
    1.11
    holds
    1.10
    Activations Density 0.464%

    No Known Activations