© 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. 13300
    Prev
    Next
    INDEX
    Explanations

    and/or connectors

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

    concepts connected by 'and'

    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
     THESE
    0.35
     ELL
    0.31
     B
    0.31
     ANYTHING
    0.31
     THIS
    0.30
     WAR
    0.29
    某
    0.29
    有问题
    0.28
    这两
    0.28
    NOTE
    0.28
    POSITIVE LOGITS
     और
    0.54
     и
    0.54
     και
    0.54
    และ
    0.52
     ਅਤੇ
    0.49
     এবং
    0.49
     અને
    0.49
     và
    0.48
     ಮತ್ತು
    0.47
     و
    0.46
    Activations Density 0.063%

    No Known Activations