© 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. 24394
    Prev
    Next
    INDEX
    Explanations

    founder company

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

    company or founder

    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
     peut
    0.50
    গ
    0.49
    カ
    0.49
    或
    0.48
    方
    0.47
    ’
    0.46
    不
    0.46
    ಫ
    0.46
    浅
    0.46
    𝘮
    0.46
    POSITIVE LOGITS
     لندن
    0.63
     perusahaan
    0.60
     şirket
    0.59
     الشركة
    0.59
    创始人
    0.58
     şirk
    0.57
     vuonna
    0.56
     founder
    0.55
     компания
    0.55
     संस्थापक
    0.55
    Activations Density 0.000%

    No Known Activations