© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95709
    Prev
    Next
    INDEX
    Explanations

    service provider or relay team

    np_acts-logits-general · gemini-2.5-flash-lite

    ecological themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    迭代
    0.48
    ativo
    0.47
    Фе
    0.47
    雕
    0.47
    ፍተኛ
    0.47
    Кон
    0.46
    iteration
    0.46
    페
    0.46
    Iterations
    0.46
    apiKey
    0.45
    POSITIVE LOGITS
     Sikh
    0.51
     Calcd
    0.48
     auprès
    0.46
     INDIA
    0.46
     मतलब
    0.46
     Sikhs
    0.46
     liye
    0.45
    ื้อง
    0.45
     ved
    0.45
     ayurved
    0.44
    Activations Density 0.003%

    No Known Activations