© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207219
    Prev
    Next
    INDEX
    Explanations

    directed to members

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

    Renaissance painting, stored in, eliminating fluid

    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
    Negative Logits
    䢁
    0.47
    سا
    0.46
    సా
    0.45
    eres
    0.45
    א
    0.44
    凌晨
    0.44
    athl
    0.43
    РИ
    0.43
    さ
    0.43
     magní
    0.42
    POSITIVE LOGITS
     सुझाव
    0.50
     कमजोरी
    0.50
     可愛
    0.47
     misplaced
    0.45
     oops
    0.45
    nikiem
    0.45
     oven
    0.44
     weakened
    0.44
     হয়তো
    0.44
     हरकत
    0.43
    Activations Density 0.000%

    No Known Activations