© 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. 10-GEMMASCOPE-RES-131K
    7. 15045
    Prev
    Next
    INDEX
    Explanations

    pedestrian contexts and foot movement

    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
    </b>
    -2.19
    _
    -1.87
    </h5>
    -1.54
     Saltar
    -1.49
    绚
    -1.48
     другие
    -1.48
    </h6>
    -1.48
     WHICH
    -1.45
     kurz
    -1.43
     leder
    -1.43
    POSITIVE LOGITS
     These
    2.19
     Эти
    1.88
    縢
    1.80
     Здесь
    1.75
     budete
    1.73
    this
    1.69
    你是不是
    1.66
    と思われます
    1.66
    社區
    1.62
     Только
    1.61
    Activations Density 0.005%

    No Known Activations