© 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. 77853
    Prev
    Next
    INDEX
    Explanations

    produces, to, into, produce, form, generate

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

    chemical reactions and products

    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
    筮
    0.44
    selective
    0.42
     загряз
    0.41
     способности
    0.40
    튼
    0.40
    柺
    0.39
    ่น
    0.38
    捨て
    0.38
     approximate
    0.37
     redundant
    0.37
    POSITIVE LOGITS
     niños
    0.41
     gada
    0.40
    ärg
    0.39
     acon
    0.38
     bilgi
    0.38
     juara
    0.38
     Mehta
    0.38
     niño
    0.38
    Kuch
    0.38
    odings
    0.38
    Activations Density 0.011%

    No Known Activations