© 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. 20109
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

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

    parentheses with numbers and operators

    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
     تاج
    0.45
     হাঁট
    0.44
    <unused171>
    0.44
     Negotiations
    0.43
     новые
    0.42
    াবলী
    0.41
     ومع
    0.41
     絵
    0.41
     negotiations
    0.40
     коро
    0.40
    POSITIVE LOGITS
     răsp
    0.48
    キ
    0.47
    -(
    0.44
    權
    0.43
    +(
    0.42
    道
    0.42
    ḳ
    0.42
    cción
    0.42
    D
    0.41
    $-(
    0.41
    Activations Density 0.008%

    No Known Activations