© 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. 191691
    Prev
    Next
    INDEX
    Explanations

    universal nature

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

    alternating sequences, patterns, distinctions

    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
    在
    0.50
    In
    0.47
    Seeing
    0.45
    Founded
    0.45
    Stat
    0.44
    IS
    0.42
    Built
    0.42
    Beyond
    0.42
    有利
    0.42
    易
    0.41
    POSITIVE LOGITS
    リューション
    0.50
     raison
    0.49
     stoichiometry
    0.48
     correctness
    0.48
    zte
    0.47
     seznam
    0.47
     مردم
    0.46
     endemic
    0.46
     hémorro
    0.45
     condoms
    0.45
    Activations Density 0.000%

    No Known Activations