© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10970
    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
    un
    1.18
    od
    1.01
    -
    0.99
    oc
    0.95
    _
    0.94
    ut
    0.93
    ul
    0.92
    an
    0.91
    ong
    0.89
    ot
    0.88
    POSITIVE LOGITS
     Lyric
    1.02
     Watertown
    0.92
     Emphasis
    0.90
     Nathalie
    0.87
     Voice
    0.85
     Ayrıca
    0.85
     Enrollment
    0.84
     CAE
    0.84
     Xinhua
    0.83
     Notification
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.