© 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. 25728
    Prev
    Next
    INDEX
    Explanations

    production

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

    production environments

    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
     tę
    0.82
     ۸
    0.72
     dukungan
    0.71
    .')
    0.71
     ৬
    0.70
     stronę
    0.70
     membentuk
    0.69
     крупней
    0.69
     `'\\
    0.68
     berupa
    0.68
    POSITIVE LOGITS
    生产
    1.23
    生產
    1.18
    Production
    1.14
    生産
    1.09
     Production
    1.08
     production
    1.05
     생산
    0.98
     PRODUCTION
    0.97
    production
    0.96
     productie
    0.95
    Activations Density 0.052%

    No Known Activations