© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10749
    Prev
    Next
    INDEX
    Explanations

    at http links

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

    https links

    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_40_width_16k_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
     органов
    0.49
    関連項目
    0.39
    onso
    0.39
    кансер
    0.37
     Vorsitz
    0.37
    ́
    0.37
     हिन्द
    0.37
    )}`;
    0.36
     coals
    0.36
    目錄
    0.36
    POSITIVE LOGITS
     https
    2.41
    https
    2.38
     http
    2.22
    http
    2.19
    ttps
    1.27
     www
    1.20
    Https
    1.01
    httphttps
    0.98
    www
    0.95
    ttp
    0.90
    Activations Density 0.183%

    No Known Activations