© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57090
    Prev
    Next
    INDEX
    Explanations

    digital game downloads

    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
    шай
    -0.83
     Fluss
    -0.73
    ҹ
    -0.72
    htb
    -0.71
     RSV
    -0.70
     benzo
    -0.70
    Printed
    -0.70
    ཻ
    -0.69
    ância
    -0.69
     cardio
    -0.68
    POSITIVE LOGITS
     download
    1.42
     PSN
    1.32
     downloads
    1.27
     downloadable
    1.27
    Download
    1.13
    download
    1.09
     Download
    1.06
     downloading
    1.05
    配信
    1.02
     digital
    1.02
    Activations Density 0.029%

    No Known Activations