© 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. 131660
    Prev
    Next
    INDEX
    Explanations

    providing, offering, helping

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

    provides

    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
     aliv
    0.44
     univer
    0.44
     típica
    0.40
     pivoted
    0.39
    ណ្ឌ
    0.38
    unic
    0.37
    namespaces
    0.37
     (=
    0.37
     losers
    0.37
     tivesse
    0.36
    POSITIVE LOGITS
    提供
    0.73
     fournir
    0.70
     提供
    0.70
    帮忙
    0.68
    提供了
    0.66
    贡献
    0.65
     provide
    0.64
    provide
    0.63
    Provide
    0.61
    Providing
    0.61
    Activations Density 0.359%

    No Known Activations