© 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. 92200
    Prev
    Next
    INDEX
    Explanations

    starts with punctuation

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

    time and communication delays

    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
    が良い
    0.48
    0
    0.47
     больш
    0.47
    ◻
    0.46
    н
    0.46
    ј
    0.46
    р
    0.45
     иностран
    0.44
    1
    0.44
    ᄉ
    0.44
    POSITIVE LOGITS
    尝试
    0.47
    বিত
    0.46
     entrop
    0.46
    涵盖
    0.45
     Sorrent
    0.44
     introns
    0.44
     Theories
    0.43
     Ejemplo
    0.43
     agonists
    0.43
     Duplicate
    0.42
    Activations Density 0.001%

    No Known Activations