© 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. 126091
    Prev
    Next
    INDEX
    Explanations

    review information

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

    sometimes, generally

    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
    不仅
    0.49
     όχι
    0.46
     homenagem
    0.46
     प्रवीण
    0.45
    比賽
    0.45
    رز
    0.44
    ूथ
    0.44
    觧
    0.44
     not
    0.44
    多样
    0.43
    POSITIVE LOGITS
     membran
    0.58
     motherboard
    0.55
     mitochondria
    0.54
     membrane
    0.54
     caudal
    0.51
     bifurcation
    0.50
     USB
    0.48
     mitochond
    0.48
     pedals
    0.47
     glial
    0.47
    Activations Density 0.000%

    No Known Activations