© 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. 131956
    Prev
    Next
    INDEX
    Explanations

    collocations and phrasal units

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

    potential risks

    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
    د
    0.52
    اي
    0.50
     nao
    0.49
    न्दर
    0.48
    ೆಂಟ್
    0.48
    얹
    0.47
    ين
    0.47
     zau
    0.47
    й
    0.45
    င်း
    0.44
    POSITIVE LOGITS
     Developmental
    0.52
     शास्त्रों
    0.50
    Kappa
    0.50
     ஊட்ட
    0.50
     UCC
    0.48
     Anthropology
    0.46
     developmentally
    0.45
     UNC
    0.45
     ομάδα
    0.45
     Babylon
    0.45
    Activations Density 0.000%

    No Known Activations