© 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. 71853
    Prev
    Next
    INDEX
    Explanations

    national Security Advisor

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

    dreams, Utopia, bananas, cone

    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
    Jennifer
    0.44
    Funding
    0.44
    ...">
    0.44
    é
    0.44
    Updates
    0.43
    <0x0D>
    0.42
    Upgrade
    0.42
     commerciales
    0.42
    Insights
    0.42
    {"
    0.41
    POSITIVE LOGITS
     xii
    0.48
     Agra
    0.46
     soda
    0.45
     সুতরাং
    0.45
    kerchief
    0.45
     weary
    0.45
     forth
    0.45
     mantra
    0.45
     industrious
    0.45
     Sino
    0.44
    Activations Density 0.003%

    No Known Activations