© 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. 219934
    Prev
    Next
    INDEX
    Explanations

    offer, dollars, Christmas

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

    gender roles and scientific 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
    踮
    0.47
     مهمه
    0.47
    depression
    0.44
    redirectTo
    0.43
     چھوڑ
    0.43
     معاہد
    0.43
    ozygous
    0.42
     olvidar
    0.42
     wirelessly
    0.42
    ویزی
    0.42
    POSITIVE LOGITS
    м
    0.57
    মূল
    0.48
    箱
    0.47
    ")]
    0.46
    "){
    0.46
    二
    0.45
    વ
    0.44
     deux
    0.43
    ә
    0.43
    張
    0.43
    Activations Density 0.000%

    No Known Activations