© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 736
    Prev
    Next
    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    基本的に
    -1.65
    普通の
    -1.51
     муніципалі
    -1.49
    ほどの
    -1.49
     применяется
    -1.47
     этого
    -1.44
    すでに
    -1.41
     same
    -1.41
    通常の
    -1.41
     debería
    -1.41
    POSITIVE LOGITS
    зим
    1.58
     for
    1.52
    бри
    1.41
    螄
    1.41
    Ⅰ
    1.40
     korban
    1.38
    rably
    1.37
     Diman
    1.37
    ಠ
    1.35
    
    1.35
    Activations Density 0.019%

    No Known Activations