© 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. 45138
    Prev
    Next
    INDEX
    Explanations

    produced annually

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

    lists of specific items

    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
    ytte
    0.48
    kannt
    0.48
    ectar
    0.46
    茲
    0.46
     verr
    0.44
    [:,
    0.43
     gjennom
    0.43
    )):
    0.43
    꺄
    0.43
    ؤلاء
    0.43
    POSITIVE LOGITS
     concluding
    0.47
    グループ
    0.46
     ಸಲ
    0.45
     வாக்கு
    0.45
     ovipares
    0.45
    批評
    0.45
    変化
    0.44
    まとめ
    0.44
     דבר
    0.44
     checksum
    0.44
    Activations Density 0.000%

    No Known Activations