© 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. 34-GEMMASCOPE-RES-131K
    7. 62628
    Prev
    Next
    INDEX
    Explanations

    programming or categories

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    効率
    -0.90
    سک
    -0.84
    NESOTA
    -0.82
     Tomar
    -0.79
     uname
    -0.79
     Decomposition
    -0.78
    ân
    -0.77
    خلا
    -0.77
     durian
    -0.76
    Sortie
    -0.75
    POSITIVE LOGITS
    __()
    0.92
     इन
    0.88
    atibility
    0.84
    adalajara
    0.82
    recover
    0.81
     recover
    0.80
    recovery
    0.80
     Heritage
    0.78
    WithIOException
    0.76
     продви
    0.75
    Activations Density 0.000%

    No Known Activations