© 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. 250717
    Prev
    Next
    INDEX
    Explanations

    fashion or job titles

    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
    ed
    0.48
     sizi
    0.46
    oniazid
    0.45
     उन्हें
    0.45
    iosis
    0.45
     leased
    0.45
     मील
    0.44
    ์
    0.44
    iatric
    0.44
     Peers
    0.44
    POSITIVE LOGITS
    رشف
    0.55
     hadden
    0.53
    كمة
    0.52
    ؟!
    0.48
    鄧
    0.48
    Breakpoint
    0.47
     crossbow
    0.47
    بخ
    0.46
    Francesco
    0.46
    дания
    0.45
    Activations Density 0.001%

    No Known Activations