© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14162
    Prev
    Next
    INDEX
    Explanations

    detect enemy's projectile

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

    final report or case section

    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
    тию
    0.46
    stimulating
    0.44
    determination
    0.44
    स्त्री
    0.43
    etermined
    0.43
    чення
    0.42
    Iranian
    0.42
    ″
    0.42
     attham
    0.41
    abortion
    0.41
    POSITIVE LOGITS
    产品
    0.51
    纱
    0.51
     medallions
    0.50
     decals
    0.50
     gai
    0.50
     sureties
    0.49
     trays
    0.49
     pulleys
    0.49
     pergola
    0.48
     revenue
    0.48
    Activations Density 0.000%

    No Known Activations