© 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. 233412
    Prev
    Next
    INDEX
    Explanations

    proper nouns and entities

    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
    ।
    0.50
    Không
    0.49
    にか
    0.48
     thái
    0.48
    З
    0.48
    エム
    0.46
    香味
    0.46
     عنہ
    0.45
    विशेष
    0.45
    SHOW
    0.45
    POSITIVE LOGITS
     NY
    0.52
     Brexit
    0.47
     CDC
    0.47
     Par
    0.46
    пански
    0.45
    nyt
    0.45
    )."
    0.44
     चाँ
    0.44
    oer
    0.44
    龺
    0.43
    Activations Density 0.002%

    No Known Activations