© 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. 249899
    Prev
    Next
    INDEX
    Explanations

    entering code

    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
    dum
    0.52
    ɴ
    0.44
     grammaticality
    0.43
     조회
    0.42
     Phó
    0.42
     étale
    0.42
     ними
    0.42
    SelectionSet
    0.42
     졸
    0.41
    len
    0.41
    POSITIVE LOGITS
     বাব
    0.55
     Military
    0.50
    花费
    0.50
    이면
    0.49
    inken
    0.47
     sayıda
    0.47
     CHILD
    0.46
     Tribut
    0.45
    줘
    0.44
    スタイ
    0.44
    Activations Density 0.001%

    No Known Activations