© 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. 168810
    Prev
    Next
    INDEX
    Explanations

    site descriptions

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

    pituitary gland growth

    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
    𝘏
    0.50
    𝗧
    0.48
    িনের
    0.47
    📼
    0.47
    伀
    0.46
    𝙋
    0.46
    我們的
    0.45
    ர்
    0.44
    Р
    0.44
     नम
    0.44
    POSITIVE LOGITS
     philanthrop
    0.50
     cookbook
    0.49
     fillColor
    0.47
     philanthropist
    0.46
    graphHead
    0.46
     capitalise
    0.45
     capitalize
    0.45
     macroeconomic
    0.44
     counterbalance
    0.44
     definite
    0.44
    Activations Density 0.000%

    No Known Activations