© 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. 234774
    Prev
    Next
    INDEX
    Explanations

    discourse markers or clauses

    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
    ويه
    0.46
    묭
    0.43
     footballers
    0.42
     systèmes
    0.42
     bulldozer
    0.42
    대는
    0.42
     convene
    0.41
     deber
    0.41
     εκ
    0.41
     système
    0.41
    POSITIVE LOGITS
     Candida
    0.56
    ulsion
    0.49
     Nath
    0.48
    可以
    0.46
     CNBC
    0.46
     Press
    0.45
    >
    0.45
    唳
    0.45
     मुक्ति
    0.45
     Reuters
    0.45
    Activations Density 0.000%

    No Known Activations