© 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. 59037
    Prev
    Next
    INDEX
    Explanations

    specific phrases that follow certain words

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

    curly braces `{}`

    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
    アート
    0.52
    اگ
    0.52
    iał
    0.48
    Ƅ
    0.48
     AWAY
    0.48
     व्य
    0.48
     اص
    0.46
    اد
    0.46
    ټ
    0.46
    無理
    0.45
    POSITIVE LOGITS
     jeopardize
    0.49
    ponden
    0.48
     Func
    0.47
    君
    0.46
     responsive
    0.45
    rypto
    0.44
     Gleason
    0.44
     empowerment
    0.43
    velopp
    0.43
    )})
    0.43
    Activations Density 0.000%

    No Known Activations