© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110495
    Prev
    Next
    INDEX
    Explanations

    SQL injection, quotes, upload

    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
    energy
    -0.75
     energy
    -0.71
    소
    -0.71
    主题
    -0.70
    ユー
    -0.69
    iência
    -0.69
    त
    -0.68
    нки
    -0.68
    Muslim
    -0.68
    дка
    -0.67
    POSITIVE LOGITS
     handball
    1.10
     hand
    1.04
    MAGIC
    0.99
     adds
    0.92
    magic
    0.89
     magic
    0.88
    GPC
    0.87
     hands
    0.85
     HAND
    0.82
    hands
    0.82
    Activations Density 0.019%

    No Known Activations