© 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. 88416
    Prev
    Next
    INDEX
    Explanations

    word about returns

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

    closings and starters

    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
    Ờ
    0.54
     homogé
    0.50
     convoluted
    0.49
     संस्थान
    0.48
    ង់
    0.47
     밑
    0.47
    வ்
    0.46
    motiv
    0.46
     সম্মতি
    0.46
     Atención
    0.46
    POSITIVE LOGITS
    ت
    0.48
     yksi
    0.47
     algorit
    0.47
     forse
    0.46
     ailes
    0.46
     Haft
    0.46
     amer
    0.45
     aanv
    0.45
    താണ്
    0.44
     undang
    0.44
    Activations Density 0.001%

    No Known Activations