© 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. 34-GEMMASCOPE-RES-131K
    7. 59533
    Prev
    Next
    INDEX
    Explanations

    questions about findings or adding information

    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
    íny
    -0.72
    Sí
    -0.68
    Compartir
    -0.67
     surveyed
    -0.66
    DTOs
    -0.65
    торов
    -0.65
     kitu
    -0.64
    continu
    -0.64
     plc
    -0.64
    pictureBox
    -0.64
    POSITIVE LOGITS
     informatie
    0.75
     eran
    0.71
    Classification
    0.68
    annister
    0.66
     Clear
    0.66
     INFORMATION
    0.66
    認知
    0.66
    튬
    0.66
     Accuracy
    0.65
     Bella
    0.64
    Activations Density 0.040%

    No Known Activations