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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12268
    Prev
    Next
    INDEX
    Explanations

    negation or refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    വും
    0.44
    zub
    0.43
     augment
    0.42
    u
    0.42
    ø
    0.42
     progen
    0.42
    ’
    0.42
     znovu
    0.42
    f
    0.41
    autorisation
    0.41
    POSITIVE LOGITS
    不是
    0.57
     ਨਹੀਂ
    0.55
     не
    0.51
    orescent
    0.51
     δεν
    0.50
    មិន
    0.47
    不
    0.47
     não
    0.46
     نہیں
    0.46
    not
    0.46
    Activations Density 0.019%

    No Known Activations