© 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. 56998
    Prev
    Next
    INDEX
    Explanations

    software package descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ktoré
    -1.12
     Tamaño
    -1.09
     kulinar
    -1.09
     Meksi
    -1.08
     didik
    -1.05
     konkret
    -1.05
     koš
    -1.05
     transak
    -1.04
     Mientras
    -1.03
     què
    -1.03
    POSITIVE LOGITS
     a
    2.28
     this
    1.65
     an
    1.37
     This
    1.36
     это
    1.28
    This
    1.24
    this
    1.20
     lightweight
    1.12
     repository
    1.10
     هذا
    1.09
    Activations Density 0.077%

    No Known Activations