© 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. 232359
    Prev
    Next
    INDEX
    Explanations

    institutions, validity, and distance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     countable
    0.50
     frontage
    0.48
     Puja
    0.47
     按
    0.46
     Количество
    0.46
     souvenirs
    0.45
     streams
    0.45
     numbered
    0.44
     دھ
    0.44
     immediate
    0.44
    POSITIVE LOGITS
    zk
    0.52
    {
    0.51
    질
    0.50
    zr
    0.50
    zur
    0.48
    宣
    0.48
    σ
    0.48
    zs
    0.48
    Der
    0.48
    version
    0.48
    Activations Density 0.001%

    No Known Activations