© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3808
    Prev
    Next
    INDEX
    Explanations

    introduce examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artment
    0.27
     (
    0.26
    خل
    0.25
     Від
    0.25
     нада
    0.25
     &/
    0.25
     .”
    0.25
     ‏
    0.24
    adorable
    0.24
    epam
    0.24
    POSITIVE LOGITS
     பொதுவாக
    0.36
     अन्य
    0.36
     შემთხვევაში
    0.34
     entanto
    0.33
    如果是
    0.32
     예를
    0.32
     භාවිත
    0.31
     конкре
    0.31
     других
    0.31
    一般的
    0.31
    Activations Density 0.085%

    No Known Activations