© 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. 210425
    Prev
    Next
    INDEX
    Explanations

    actions following 'to' or 'that'

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

    definition and prediction

    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
     Bantu
    0.50
    洴
    0.48
     Benoit
    0.48
     منہ
    0.47
     setEmail
    0.47
     похід
    0.46
     ट्वी
    0.46
     caratter
    0.46
     вме
    0.46
     thử
    0.46
    POSITIVE LOGITS
    background
    0.49
    status
    0.47
    continued
    0.46
    autiful
    0.45
    sp
    0.44
    mutual
    0.44
    r
    0.44
    mo
    0.44
    ased
    0.44
    folder
    0.43
    Activations Density 0.000%

    No Known Activations