© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 259027
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ró
    0.52
    ))\
    0.47
     knotted
    0.46
     কী
    0.45
     ओलंपिक
    0.44
    )}\
    0.44
     गतिविधि
    0.43
    square
    0.43
    knot
    0.43
     knot
    0.42
    POSITIVE LOGITS
    Neighbors
    0.49
    avra
    0.48
    нде
    0.48
    Views
    0.46
    льд
    0.45
     a
    0.45
    anio
    0.44
    haber
    0.44
    лім
    0.44
    вання
    0.43
    Activations Density 0.001%

    No Known Activations