© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14947
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     no
    -1.04
     there
    -0.94
    return
    -0.90
     männis
    -0.87
     These
    -0.86
     these
    -0.82
    あき
    -0.80
    romy
    -0.79
     इसमें
    -0.79
    these
    -0.79
    POSITIVE LOGITS
     Propriété
    1.02
     Durée
    0.96
    После
    0.92
     tissus
    0.91
     badań
    0.90
    grenze
    0.88
    nebo
    0.88
     eerst
    0.88
    posição
    0.88
    قایناق
    0.88
    Activations Density 0.003%

    No Known Activations