© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86673
    Prev
    Next
    INDEX
    Explanations

    inheritance of properties and traits

    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_16_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
    к
    0.91
    お問い合わせ
    0.88
     are
    0.86
    are
    0.81
    ian
    0.80
     işlemler
    0.80
    không
    0.77
    お願い
    0.77
     सिने
    0.75
     એક
    0.75
    POSITIVE LOGITS
    هم
    1.19
    ת
    1.19
    د
    1.14
    ้
    1.03
    in
    1.01
    า
    0.98
    ור
    0.96
    ב
    0.95
    -
    0.94
    הר
    0.93
    Activations Density 0.003%

    No Known Activations