© 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. 28414
    Prev
    Next
    INDEX
    Explanations

    played professionally

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

    dates, titles, companies

    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
    İ
    0.48
    package
    0.47
     isi
    0.46
    ,
    0.46
    cyl
    0.45
    ค่า
    0.45
    Village
    0.45
    Ust
    0.44
    Iss
    0.42
     nilai
    0.42
    POSITIVE LOGITS
    dataReader
    0.46
    <0x80>
    0.45
    遍历
    0.43
    badbreak
    0.43
     rozm
    0.42
     કરે
    0.42
     সম্মান
    0.41
    }{*}{
    0.40
    納
    0.40
    )*
    0.40
    Activations Density 0.000%

    No Known Activations