© 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. 210196
    Prev
    Next
    INDEX
    Explanations

    unless otherwise

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

    spouse, eating, breed, He, May

    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
    lefthar
    0.50
    कह
    0.49
    criminal
    0.48
    シップ
    0.47
     zetten
    0.47
    thinkable
    0.47
    ༧
    0.47
    祈
    0.47
    Khokhlov
    0.46
    abv
    0.46
    POSITIVE LOGITS
     Scarlett
    0.54
     Palette
    0.54
     Pencil
    0.52
     Progress
    0.52
     Sticker
    0.51
     Progression
    0.50
     Promises
    0.46
     Anth
    0.46
     Pyrénées
    0.46
     Vocabulary
    0.46
    Activations Density 0.001%

    No Known Activations