© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5765
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     wrinkled
    0.88
     ridges
    0.86
     coupling
    0.86
     tedious
    0.84
     recursive
    0.82
    与
    0.79
     caramelized
    0.79
     reusable
    0.78
     dimensionless
    0.77
     perpendicular
    0.76
    POSITIVE LOGITS
    الي
    0.89
    الأ
    0.80
     Babies
    0.77
     Sports
    0.75
    нин
    0.75
    artige
    0.75
     Giải
    0.73
     Bhavan
    0.72
     ))->
    0.71
    الان
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.