© 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. 99719
    Prev
    Next
    INDEX
    Explanations

    swept or carried away

    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
    છ
    -0.78
    Savannah
    -0.75
    ραγ
    -0.73
    ằ
    -0.73
     představ
    -0.72
     Loader
    -0.71
    AGEMENT
    -0.68
     вокруг
    -0.66
    middag
    -0.66
     засто
    -0.66
    POSITIVE LOGITS
     carried
    3.47
     swept
    2.88
     carry
    2.69
    carried
    2.67
     Carried
    2.48
    carry
    2.42
     carries
    2.41
    Carry
    2.30
     Carry
    2.27
     sweep
    2.25
    Activations Density 0.041%

    No Known Activations