© 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. 71146
    Prev
    Next
    INDEX
    Explanations

    tokens following "the"

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

    planning and coordinating actions

    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
    Iraq
    0.50
    varez
    0.46
    When
    0.44
    Coca
    0.43
    कर
    0.42
    
    0.42
     বিশ্বাস
    0.42
    league
    0.42
    ಚ್
    0.41
    ুদ্র
    0.41
    POSITIVE LOGITS
    던
    0.49
     parameterized
    0.48
     matroid
    0.46
     어머니
    0.46
     Dispon
    0.46
     آتے
    0.46
    و
    0.46
    тету
    0.45
     ہونے
    0.44
     🥰
    0.44
    Activations Density 0.001%

    No Known Activations