© 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. 64947
    Prev
    Next
    INDEX
    Explanations

    accented spanish and portuguese word fragments

    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
     Zeitraum
    -0.76
    며
    -0.73
    鉛筆
    -0.69
     schoolmaster
    -0.68
     corrente
    -0.68
    Transcripción
    -0.68
    Edmund
    -0.67
     Edmund
    -0.67
     Shin
    -0.67
     Sap
    -0.66
    POSITIVE LOGITS
     multiples
    0.96
     scorn
    0.81
     loss
    0.81
    fora
    0.77
    niker
    0.77
    гипет
    0.76
     addict
    0.75
     lī
    0.74
    istry
    0.73
     funnel
    0.73
    Activations Density 0.020%

    No Known Activations