© 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. 18831
    Prev
    Next
    INDEX
    Explanations

    crew chief

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

    list items with bullet

    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
     została
    0.27
    돛
    0.26
     ಬಳಕೆ
    0.26
    শংস
    0.26
     নৌ
    0.26
     défense
    0.25
    ระบบ
    0.25
    সিংহ
    0.25
    आवेदन
    0.25
    赭
    0.25
    POSITIVE LOGITS
    </h3>
    0.29
    </strong>
    0.27
    lar
    0.27
    ados
    0.25
    otro
    0.25
    ри
    0.24
     sl
    0.23
    ri
    0.22
     stare
    0.22
    u
    0.22
    Activations Density 0.204%

    No Known Activations