© 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. 90582
    Prev
    Next
    INDEX
    Explanations

    Twice the, global equities, microscopic ship

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

    language and technical topics

    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
    腾讯
    0.54
    azada
    0.49
    েব
    0.46
     爱
    0.46
    长度
    0.46
    imagem
    0.45
    尔
    0.44
    leme
    0.44
     Editing
    0.44
    胶
    0.44
    POSITIVE LOGITS
    രുത്
    0.49
     temor
    0.47
     parent
    0.46
     carelessly
    0.45
    うん
    0.45
     debajo
    0.44
     beho
    0.44
     underlie
    0.44
     unwarranted
    0.43
     المرحله
    0.43
    Activations Density 0.000%

    No Known Activations