© 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. 1523
    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
    াবার
    0.75
    eps
    0.71
    grams
    0.71
    gages
    0.69
    kil
    0.68
    ек
    0.67
    ф
    0.66
    ism
    0.65
     vests
    0.64
    usions
    0.63
    POSITIVE LOGITS
    ﻤ
    0.94
     bienestar
    0.90
     אך
    0.89
     العديد
    0.87
     carrito
    0.85
     スニーカー
    0.83
     المدرسة
    0.81
    SafeArea
    0.80
     canción
    0.80
    ﺸ
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.