© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3652
    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_24_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
    एस
    0.72
    AG
    0.68
    ا
    0.67
    unu
    0.66
    舒
    0.66
    нат
    0.65
    داء
    0.65
    ocket
    0.65
    ະ
    0.65
    outi
    0.64
    POSITIVE LOGITS
     thoại
    0.90
     blijven
    0.90
     ngược
    0.82
    ೆ
    0.80
    笫
    0.80
     betray
    0.79
     venezol
    0.77
     válida
    0.76
     CHCl
    0.75
     belangrijkste
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.