© 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. 144451
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    numbers in many languages

    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
    ặn
    0.43
    ante
    0.40
     pulau
    0.40
     በማ
    0.39
    羮
    0.39
     हल्के
    0.38
     एखाद्या
    0.38
     ರೀತಿಯ
    0.38
     chup
    0.38
     عايزين
    0.38
    POSITIVE LOGITS
     sechs
    0.53
     zwölf
    0.52
     seventy
    0.51
    四十
    0.51
     fifty
    0.50
     sixty
    0.50
     шесть
    0.49
     семи
    0.48
    ６
    0.47
     १२
    0.47
    Activations Density 0.000%

    No Known Activations