© 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. 1301
    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
     (
    0.59
     denominada
    0.53
     universitaire
    0.52
     governmental
    0.52
     domic
    0.51
     desktops
    0.51
     sectoral
    0.50
     biota
    0.50
     monetary
    0.49
     haupt
    0.49
    POSITIVE LOGITS
    פ
    0.61
    Jug
    0.57
    Haha
    0.56
    ורה
    0.55
    Param
    0.55
    מה
    0.54
    En
    0.54
    Anton
    0.54
    SOR
    0.53
    ור
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.