© 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. 99116
    Prev
    Next
    INDEX
    Explanations

    company websites and discounts

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

    Chinese names and places

    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
    ند
    0.46
     indiquant
    0.40
     Ecke
    0.40
    자
    0.40
     sempl
    0.38
    جا
    0.38
    ٠
    0.38
    س
    0.38
     ordinairement
    0.38
     aliments
    0.38
    POSITIVE LOGITS
    কোষ
    0.48
     ભાગ
    0.46
     খানের
    0.45
    ન્યા
    0.44
     ভাঙ
    0.44
     व्यापारी
    0.43
    出演
    0.43
    цията
    0.42
     thành
    0.42
    orthogonal
    0.42
    Activations Density 0.001%

    No Known Activations