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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12574
    Prev
    Next
    INDEX
    Explanations

    timeout parameter

    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
     Joyce
    0.44
    Joyce
    0.43
    barung
    0.43
    鎊
    0.42
     Females
    0.41
    établissement
    0.40
    പ്പിക്ക
    0.39
     स्त्रियों
    0.38
    ্স্ট
    0.38
    テイン
    0.38
    POSITIVE LOGITS
     z
    0.39
    ?;
    0.38
    _
    0.38
     з
    0.38
    є
    0.36
     CC
    0.35
     които
    0.35
     пра
    0.35
    Rotation
    0.35
     CFA
    0.35
    Activations Density 0.207%

    No Known Activations