© 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. 235531
    Prev
    Next
    INDEX
    Explanations

    exceptions to this

    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
    deki
    0.47
    oł
    0.47
     volts
    0.46
    オブジェクト
    0.45
    퐁
    0.45
    סי
    0.45
    də
    0.45
    ל
    0.44
    מ
    0.44
    volle
    0.44
    POSITIVE LOGITS
    厳しい
    0.44
     крайней
    0.43
     कंप्यूट
    0.42
     жё
    0.42
     yerden
    0.42
    shaders
    0.41
     Вайлд
    0.41
     harsher
    0.40
     уста
    0.40
    ্বেও
    0.40
    Activations Density 0.000%

    No Known Activations