© 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. 231979
    Prev
    Next
    INDEX
    Explanations

    continue after order

    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
    纶
    0.46
    数为
    0.45
    бре
    0.44
    clipse
    0.44
    ọn
    0.43
    anke
    0.43
    kelijk
    0.43
    qi
    0.42
    谦
    0.41
    本次
    0.40
    POSITIVE LOGITS
    െ
    0.57
    ента
    0.52
    ו
    0.48
     взять
    0.47
    Unh
    0.47
     موسي
    0.46
    فيد
    0.45
     استخدم
    0.44
    ůli
    0.44
    سين
    0.44
    Activations Density 0.000%

    No Known Activations