© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5600
    Prev
    Next
    INDEX
    Explanations

    less or greater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    m
    0.94
    م
    0.90
    '
    0.72
    吧
    0.70
    s
    0.70
    session
    0.69
    }}=(
    0.69
    벼
    0.69
    って
    0.68
    ುತ್ತಿದೆ
    0.68
    POSITIVE LOGITS
     awakened
    0.87
     conjuntos
    0.81
     plagued
    0.80
     ascertained
    0.78
     exaggerated
    0.77
     synced
    0.77
     aguj
    0.76
     sacerd
    0.75
     hastened
    0.75
     awakens
    0.75
    Activations Density 0.000%

    No Known Activations