© 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. 204006
    Prev
    Next
    INDEX
    Explanations

    best, shape, lighting, necessary

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

    calculate the

    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
    均为
    0.49
    虚
    0.46
    均
    0.46
     Voy
    0.45
    くい
    0.45
    頂
    0.45
    สิ้น
    0.44
    顶
    0.44
    Void
    0.43
    Ils
    0.43
    POSITIVE LOGITS
     entails
    0.51
     dependences
    0.48
     companionship
    0.47
     excludes
    0.46
    ्रमण
    0.46
     narrates
    0.46
     enriching
    0.45
     dalamnya
    0.44
     compreender
    0.44
     chlorinated
    0.44
    Activations Density 0.001%

    No Known Activations