© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54220
    Prev
    Next
    INDEX
    Explanations

    AP datelines and punctuation

    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
     também
    -1.04
     Также
    -1.00
     источник
    -0.95
    ifed
    -0.93
     également
    -0.93
    UObject
    -0.90
     También
    -0.90
     pantalón
    -0.90
     to
    -0.89
     maravillosa
    -0.89
    POSITIVE LOGITS
    Plusieurs
    1.09
     –
    1.09
     -
    1.00
    Quelques
    0.93
    Combien
    0.91
    Beaucoup
    0.91
    Même
    0.90
    Peut
    0.90
    Newly
    0.87
     Spirito
    0.86
    Activations Density 0.082%

    No Known Activations