© 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. 38929
    Prev
    Next
    INDEX
    Explanations

    floor plans

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

    specialized terms and abbreviations

    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
    ación
    0.57
    érist
    0.53
    ።
    0.52
    eringen
    0.51
    ulsion
    0.51
    ácio
    0.51
    agio
    0.49
    édie
    0.49
    𝙻
    0.49
    Marie
    0.48
    POSITIVE LOGITS
     fondamental
    0.50
    ヒト
    0.47
     mammary
    0.46
     ঔষধ
    0.43
    ยู
    0.43
    нд
    0.43
    щими
    0.43
    シャ
    0.43
     raggiungere
    0.43
    снов
    0.43
    Activations Density 0.000%

    No Known Activations