© 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. 180857
    Prev
    Next
    INDEX
    Explanations

    shopping for specific items

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

    difference between

    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
     až
    0.54
    boBox
    0.46
     đạt
    0.45
    ាតុ
    0.45
     cán
    0.44
    ষ্টার
    0.44
    -"+
    0.44
    vay
    0.44
     nových
    0.44
    粔
    0.43
    POSITIVE LOGITS
     Luna
    0.46
     glorified
    0.45
     manufactured
    0.44
    Г
    0.44
    様々な
    0.44
    ғ
    0.44
     programmed
    0.43
     photographs
    0.43
     sabbatical
    0.42
     Фото
    0.42
    Activations Density 0.001%

    No Known Activations