© 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. 22-GEMMASCOPE-RES-131K
    7. 33210
    Prev
    Next
    INDEX
    Explanations

    values and properties

    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_22/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
     geweldig
    -0.98
    责编
    -0.96
    ГЛА
    -0.90
    OrderBy
    -0.88
    ństwo
    -0.87
    奈良
    -0.87
    futbolista
    -0.85
     başar
    -0.84
     Spanyol
    -0.84
    誰も
    -0.83
    POSITIVE LOGITS
     values
    0.98
     their
    0.96
    type
    0.96
     type
    0.90
     value
    0.89
     they
    0.89
     contribution
    0.89
     تغذیه
    0.88
     relationship
    0.88
    uação
    0.86
    Activations Density 0.020%

    No Known Activations