© 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. 213283
    Prev
    Next
    INDEX
    Explanations

    "condition" followed by consequence

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

    encourage or promote action

    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
    缩
    0.48
    ший
    0.47
    สาร
    0.46
    糸
    0.45
    辋
    0.45
     Links
    0.44
    弘
    0.44
    возможно
    0.44
    玮
    0.44
     possibly
    0.42
    POSITIVE LOGITS
     fio
    0.51
     muestras
    0.50
     mengan
    0.50
     ہمارے
    0.49
    pared
    0.48
    OVER
    0.48
     thisTrack
    0.47
     }_{\
    0.47
     ôn
    0.47
     द्वारा
    0.46
    Activations Density 0.001%

    No Known Activations