© 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. 114502
    Prev
    Next
    INDEX
    Explanations

    time zones and locations

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

    text-to-image

    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
    创意
    0.59
    🏤
    0.58
     నగ
    0.57
    नेश
    0.56
     구매
    0.55
     시장
    0.55
    振兴
    0.55
    गांव
    0.54
    公园
    0.54
    举办
    0.54
    POSITIVE LOGITS
     bimodule
    0.56
     kernels
    0.54
     Hadamard
    0.53
     eigenvalues
    0.52
     {\
    0.52
     polynomials
    0.52
    -{\
    0.51
    (-\
    0.50
     \
    0.50
    ,\\
    0.50
    Activations Density 0.024%

    No Known Activations