© 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. 80520
    Prev
    Next
    INDEX
    Explanations

    apostrophe followed by proper names

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

    words with apostrophes

    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
    विध
    0.44
     Nigam
    0.42
    的和
    0.39
    Boat
    0.38
    ryk
    0.38
    Ak
    0.38
    Opens
    0.38
    咙
    0.37
    icles
    0.37
    Kan
    0.37
    POSITIVE LOGITS
    িল
    0.50
    ä
    0.49
    то
    0.48
    á
    0.46
    ัว
    0.45
    ্সি
    0.44
     שא
    0.44
     ofthe
    0.43
    ー
    0.43
     that
    0.42
    Activations Density 0.011%

    No Known Activations