© 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. 241900
    Prev
    Next
    INDEX
    Explanations

    emergency alert system

    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
     arsenic
    0.53
    ایر
    0.49
     protons
    0.48
    업
    0.48
    उन
    0.48
     glycoproteins
    0.48
    าด
    0.47
    ир
    0.47
     receivable
    0.46
     regulates
    0.46
    POSITIVE LOGITS
    i
    0.53
    es
    0.52
    ffa
    0.50
    kenn
    0.49
     Mer
    0.48
    for
    0.48
    rique
    0.47
    success
    0.47
    ponente
    0.47
    tta
    0.47
    Activations Density 0.000%

    No Known Activations