© 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. 243633
    Prev
    Next
    INDEX
    Explanations

    day then month

    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
    ولت
    0.49
    াবা
    0.48
    碱
    0.48
    ﺹ
    0.48
    ক্র
    0.45
    轴
    0.44
     ethn
    0.44
    Strom
    0.44
    ﮗ
    0.44
    სი
    0.43
    POSITIVE LOGITS
    a
    0.52
    ́i
    0.49
     debo
    0.48
     દેશ
    0.46
     vàng
    0.45
     miš
    0.45
     chú
    0.44
     clínicas
    0.44
     रखें
    0.44
     núi
    0.43
    Activations Density 0.001%

    No Known Activations