© 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. 65013
    Prev
    Next
    INDEX
    Explanations

    Batyrev, Batley, Batak, Bataviana, Batanes, Bats

    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
    riles
    -0.78
     Angaben
    -0.76
     recou
    -0.75
    bruch
    -0.73
     hjælpe
    -0.72
    绥
    -0.71
     assistance
    -0.71
     hjælp
    -0.70
     fortitude
    -0.70
     Ländern
    -0.70
    POSITIVE LOGITS
     Noticias
    0.90
    罷
    0.78
    boné
    0.73
    äu
    0.72
     sonar
    0.72
    Tratamiento
    0.72
    InOrder
    0.71
    voje
    0.71
     taro
    0.71
    comboBox
    0.71
    Activations Density 0.024%

    No Known Activations