© 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. 10-GEMMASCOPE-RES-131K
    7. 87221
    Prev
    Next
    INDEX
    Explanations

    film titles and song names

    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_10/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
     we
    -1.82
     this
    -1.70
     it
    -1.66
     currently
    -1.64
     today
    -1.62
     estamos
    -1.58
     they
    -1.56
    🪛
    -1.55
     already
    -1.54
     you
    -1.48
    POSITIVE LOGITS
     berkenaan
    1.90
    💽
    1.67
     after
    1.65
     selepas
    1.57
     with
    1.55
     използ
    1.55
     menganggap
    1.52
    Despite
    1.41
     from
    1.41
     hongos
    1.40
    Activations Density 0.709%

    No Known Activations