© 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. 37825
    Prev
    Next
    INDEX
    Explanations

    on the air

    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
    FileType
    -0.73
     bubuk
    -0.71
     Quarte
    -0.68
    jestic
    -0.66
     Epit
    -0.66
     אני
    -0.65
     Apos
    -0.64
    $__
    -0.64
     zav
    -0.63
     sodass
    -0.62
    POSITIVE LOGITS
     air
    5.00
    air
    3.47
    Air
    2.91
     Air
    2.69
    AIR
    2.44
    空气
    2.27
     AIR
    2.23
     воздух
    2.17
     aire
    2.05
     lucht
    2.03
    Activations Density 0.037%

    No Known Activations