© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5355
    Prev
    Next
    INDEX
    Explanations

    prefixes like non-, multi-, pre-, post-, anti-

    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
     Oberfläche
    0.34
     মুক্তিফৌজ
    0.31
    Კ
    0.31
     encuentra
    0.31
    ফটেন
    0.30
     heure
    0.29
    शिलाजीत
    0.29
    دی
    0.29
     Brahm
    0.29
     huile
    0.29
    POSITIVE LOGITS
    -
    0.74
    ‐
    0.57
    ­
    0.51
    ־
    0.47
    -​
    0.40
    
    0.40
    ‑
    0.38
    
    0.37
    ¬
    0.35
    -,
    0.34
    Activations Density 0.342%

    No Known Activations