© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106860
    Prev
    Next
    INDEX
    Explanations

    plugin deals

    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
     on
    -0.89
     Verkaufs
    -0.77
     caucus
    -0.75
     ostensibly
    -0.75
     referred
    -0.73
     regarding
    -0.72
     revised
    -0.71
     reduce
    -0.71
     facilitates
    -0.71
     with
    -0.70
    POSITIVE LOGITS
     библиоте
    1.02
     DEAL
    0.94
     library
    0.91
     Kontakt
    0.91
     церемо
    0.88
    dry
    0.88
    Ặ
    0.88
     manier
    0.87
     коллекции
    0.87
    пол
    0.84
    Activations Density 0.016%

    No Known Activations