© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45674
    Prev
    Next
    INDEX
    Explanations

    загружать, записывать, брать

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    {
    -3.52
    嚒
    -2.28
     jums
    -2.23
    쩡
    -2.20
     ilumin
    -2.16
     textView
    -2.13
     aprove
    -2.13
    颀
    -2.11
    יסט
    -2.08
     doces
    -2.05
    POSITIVE LOGITS
     According
    2.34
     of
    2.22
    O
    2.19
    需要
    2.09
     were
    2.08
     Mostly
    2.08
    u
    2.08
    I
    2.06
     financières
    2.03
    Like
    1.98
    Activations Density 0.009%

    No Known Activations