© 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. 205210
    Prev
    Next
    INDEX
    Explanations

    specialized education titles

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

    aaaaaaaaaaaaaaaa

    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
    порта
    0.48
    ポート
    0.48
     海外
    0.45
     этап
    0.44
     interrogation
    0.44
     intellect
    0.43
    פור
    0.43
    ノ
    0.43
     extracts
    0.43
     irre
    0.42
    POSITIVE LOGITS
    aredPreferences
    0.49
    Maine
    0.48
    ț
    0.48
    ValueOf
    0.46
    DLJ
    0.46
    INFO
    0.46
    رائی
    0.45
    を守
    0.45
    Arrow
    0.45
    Ș
    0.45
    Activations Density 0.001%

    No Known Activations