© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16334
    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
    しまう
    0.82
    ش
    0.80
     остров
    0.73
    リ
    0.73
     Tvam
    0.71
    Issledovatel
    0.71
     Moul
    0.70
    انج
    0.68
     Ply
    0.68
     Auf
    0.67
    POSITIVE LOGITS
    एस
    0.76
     sophistication
    0.70
    0
    0.69
    ૦
    0.68
    ished
    0.67
     depreciation
    0.66
    DIST
    0.66
     burglary
    0.66
    ிரி
    0.66
    єр
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.