© 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. 3270
    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
    い
    0.91
     CaCO
    0.89
     épaisse
    0.86
    いる
    0.84
    样的
    0.82
    訳
    0.81
    ୟ
    0.81
    िया
    0.80
    过于
    0.80
    ি
    0.80
    POSITIVE LOGITS
    EL
    0.75
    rak
    0.70
     mire
    0.70
    ten
    0.65
     sem
    0.65
    IL
    0.64
    ssä
    0.64
     cor
    0.63
     espionage
    0.63
     pul
    0.63
    Activations Density 0.000%

    No Known Activations