© 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. 82854
    Prev
    Next
    INDEX
    Explanations

    people buying or acting

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

    variable AV block"

    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
    d
    0.45
    elajaran
    0.44
    dick
    0.44
    و
    0.43
    ˈ
    0.41
    고
    0.41
    dain
    0.41
    у
    0.40
     vous
    0.40
     phosphor
    0.40
    POSITIVE LOGITS
    状態
    0.48
     returnPacket
    0.48
     minif
    0.46
     minis
    0.44
     POLITICAL
    0.43
    Community
    0.43
     нарушение
    0.43
    Political
    0.43
     ①
    0.43
    Implementing
    0.42
    Activations Density 0.001%

    No Known Activations