© 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. 41-GEMMASCOPE-2-RES-65K
    7. 12984
    Prev
    Next
    INDEX
    Explanations

    hang

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    押
    0.59
     დაი
    0.57
    밟
    0.56
    立つ
    0.54
     gras
    0.53
     ठहर
    0.52
     sit
    0.50
     DCHECK
    0.50
    лаш
    0.50
     спла
    0.50
    POSITIVE LOGITS
     pend
    1.79
     suspended
    1.79
     pendulum
    1.77
     Pend
    1.66
    suspended
    1.62
    Pend
    1.60
    pend
    1.56
     swing
    1.55
    悬
    1.55
     pendent
    1.54
    Activations Density 0.047%

    No Known Activations