© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13516
    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
    。”
    0.32
    และ
    0.31
    。
    0.31
     เพราะ
    0.31
     BECAUSE
    0.31
    ។
    0.31
    ։
    0.30
    ۔
    0.30
    เพราะ
    0.29
    .。
    0.29
    POSITIVE LOGITS
     an
    0.34
     a
    0.34
    0.34
     the
    0.33
     yksi
    0.29
     your
    0.29
     lightweight
    0.27
     various
    0.27
     kaleidoscopic
    0.27
     eponymous
    0.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.