© 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. 198619
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    sensations or address

    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
    ни
    0.52
     HR
    0.50
    ِل
    0.48
    ниц
    0.47
    把他
    0.47
     Bich
    0.46
    ্ন
    0.45
    dSample
    0.45
     Vergangenheit
    0.45
     Wil
    0.45
    POSITIVE LOGITS
     as
    0.47
     scont
    0.47
     pasti
    0.47
    ванням
    0.47
     kreativ
    0.45
     atât
    0.45
    癡
    0.45
     diretto
    0.44
    以上に
    0.44
    oliko
    0.44
    Activations Density 0.001%

    No Known Activations