© 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. 237176
    Prev
    Next
    INDEX
    Explanations

    appointment scheduling and information recording

    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
    the
    0.46
    优质
    0.44
     indifference
    0.42
    d
    0.41
     Ether
    0.40
     Hal
    0.40
     Marin
    0.39
     ED
    0.39
     Share
    0.39
     PHA
    0.39
    POSITIVE LOGITS
    chtigt
    0.44
    ताव
    0.43
     насо
    0.43
    続け
    0.43
    র্ঘট
    0.41
    日まで
    0.41
    🤫
    0.41
     посвящён
    0.41
    궪
    0.40
    続けて
    0.40
    Activations Density 0.003%

    No Known Activations