© 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. 99276
    Prev
    Next
    INDEX
    Explanations

    coordinate meetings

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

    explains or describes actions

    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
     ใจ
    0.51
    жал
    0.51
    '',
    0.47
    ionais
    0.47
    -',
    0.46
    ोल
    0.45
     milliers
    0.45
    йо
    0.45
    +"','"+
    0.45
    oS
    0.44
    POSITIVE LOGITS
    you
    0.52
     Ex
    0.51
     व्यंजनों
    0.50
     $
    0.49
     handcrafted
    0.48
     एंट
    0.45
    ts
    0.45
    lli
    0.44
    icletas
    0.44
     Issuer
    0.44
    Activations Density 0.001%

    No Known Activations