© 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. 218581
    Prev
    Next
    INDEX
    Explanations

    prevent pain

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

    mathematical and logical concepts

    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
    對
    0.48
    建議
    0.45
     дро
    0.44
    を生
    0.44
    菲
    0.43
    協
    0.43
    審
    0.43
    來源
    0.43
    季
    0.43
    羥
    0.43
    POSITIVE LOGITS
    a
    0.57
    .**
    0.52
    .],
    0.51
    ı
    0.51
     hilly
    0.50
     bumpy
    0.48
     bed
    0.48
     ita
    0.48
    .].
    0.48
     wrinkles
    0.47
    Activations Density 0.001%

    No Known Activations