© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3710
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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_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
    (
    0.39
    ز
    0.37
     نیز
    0.34
    9
    0.33
     также
    0.33
     arī
    0.33
     incorporates
    0.32
    8
    0.32
    وس
    0.30
     arbet
    0.30
    POSITIVE LOGITS
    ’
    0.42
    囷
    0.39
    '
    0.38
    <0x19>
    0.37
     بچوں
    0.36
    тың
    0.36
    আমি
    0.35
    missing
    0.35
    нибудь
    0.34
    หว่าง
    0.33
    Activations Density 0.003%

    No Known Activations