© 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. 130514
    Prev
    Next
    INDEX
    Explanations

    research and future directions

    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
    Explicación
    -1.13
    これらの
    -1.04
     interesses
    -1.04
     recurrir
    -1.04
    YNAMICS
    -1.03
     desplazamiento
    -1.02
    Sú
    -1.01
    馔
    -1.01
     摄影
    -1.01
     använder
    -1.00
    POSITIVE LOGITS
     further
    1.55
     research
    1.27
    কা
    1.15
     future
    1.10
     extend
    1.09
     extending
    1.01
     should
    1.00
    tamide
    0.98
     continue
    0.96
     in
    0.94
    Activations Density 0.032%

    No Known Activations