© 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. 65094
    Prev
    Next
    INDEX
    Explanations

    GNU Lesser

    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
     just
    -0.81
    Montana
    -0.80
     tries
    -0.80
    fxml
    -0.78
     image
    -0.73
    keyCode
    -0.71
     stroom
    -0.71
     tried
    -0.71
     medicamento
    -0.71
    权威
    -0.71
    POSITIVE LOGITS
    omitempty
    0.82
     Tallahassee
    0.82
    Lire
    0.81
    Largura
    0.80
    Zna
    0.77
    Recep
    0.77
     obicei
    0.77
    畴
    0.76
     responsabilità
    0.75
    voici
    0.75
    Activations Density 0.001%

    No Known Activations