© 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. 72160
    Prev
    Next
    INDEX
    Explanations

    conservative and proper

    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
    dellín
    -1.33
    eningrad
    -1.27
    ApJ
    -1.25
     Returns
    -1.25
    蹰
    -1.22
    螣
    -1.18
    ྵ
    -1.18
    mtliche
    -1.18
     információk
    -1.16
    Australie
    -1.16
    POSITIVE LOGITS
    if
    1.59
    ”,
    1.59
    H
    1.47
     funktioner
    1.46
    and
    1.45
    but
    1.43
    aaaaaa
    1.43
    :[{
    1.42
     prerequisites
    1.37
     Inhalts
    1.34
    Activations Density 0.040%

    No Known Activations