Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8174
    Prev
    Next
    INDEX
    Explanations

    Kav, Kaw, or Cav followed by names

    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_34/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
    ňte
    -0.82
     할
    -0.78
    aliere
    -0.69
    🦵
    -0.69
    ńcz
    -0.69
     ramo
    -0.69
     辛
    -0.69
     chua
    -0.69
     خواه
    -0.69
    ы
    -0.69
    POSITIVE LOGITS
    tius
    0.85
    /***
    
    0.84
    hept
    0.77
    chero
    0.75
    すじ
    0.75
    参り
    0.75
     shrinking
    0.75
     BT
    0.74
     "}";
    0.74
    疽
    0.73
    Activations Density 0.015%

    No Known Activations