© 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. 7366
    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
    🏭
    0.36
    鋃
    0.35
     অর্চন
    0.35
     desar
    0.33
     insofar
    0.33
    🛑
    0.32
     aquellas
    0.31
    deload
    0.31
     столь
    0.31
    🚫
    0.31
    POSITIVE LOGITS
    2
    0.50
    3
    0.49
    4
    0.48
    0
    0.44
     a
    0.44
    5
    0.43
     the
    0.42
    0.39
    1
    0.39
    6
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.