© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92340
    Prev
    Next
    INDEX
    Explanations

    service records, embedded development, private chef, Toyota discontinued

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

    evolving or list

    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
    Negative Logits
    𝟕
    0.52
     おい
    0.52
    ҽ
    0.49
    āv
    0.48
     recalculated
    0.48
     හ
    0.46
     ベージュ
    0.46
     옛
    0.46
    рая
    0.46
     ㄱ
    0.45
    POSITIVE LOGITS
     நிறுவன
    0.50
    رحبا
    0.49
     gruppi
    0.48
     scripture
    0.47
    نة
    0.46
    কে
    0.45
    த்திற்கு
    0.45
    设备
    0.45
     نسبت
    0.45
    نوان
    0.45
    Activations Density 0.002%

    No Known Activations