© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14048
    Prev
    Next
    INDEX
    Explanations

    Python libraries and testing

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

    python api development

    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_16k_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
    jTextField
    0.49
    ခြ
    0.47
    ତ
    0.46
    粞
    0.46
    ],//
    0.45
    redirectTo
    0.45
    iffo
    0.44
    toArray
    0.43
    ভূত
    0.43
    renderCamera
    0.43
    POSITIVE LOGITS
     FastAPI
    0.84
     fastapi
    0.79
     pathlib
    0.73
     asyncio
    0.73
     pytest
    0.70
    pytest
    0.66
     kwargs
    0.63
     SQLAlchemy
    0.62
     ChatGPT
    0.62
    🥳
    0.62
    Activations Density 0.001%

    No Known Activations