© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 245975
    Prev
    Next
    INDEX
    Explanations

    specific word pairs

    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
    FileData
    0.50
     kami
    0.49
    koj
    0.49
     เจอ
    0.47
     Copeland
    0.47
     魔
    0.47
     Kog
    0.47
     Guys
    0.46
    Kami
    0.46
    Guys
    0.46
    POSITIVE LOGITS
     Mediterranean
    0.50
    ро
    0.48
    в
    0.47
    誤差
    0.46
    する
    0.45
    ול
    0.45
    ார்
    0.45
    اً
    0.44
    '
    0.44
    ор
    0.44
    Activations Density 0.001%

    No Known Activations