© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15772
    Prev
    Next
    INDEX
    Explanations

    hum or lum

    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
     específicamente
    0.65
     specifically
    0.63
     Specifically
    0.62
    Specifically
    0.61
    specifically
    0.59
     liter
    0.57
     ძ
    0.50
     టి
    0.50
     clim
    0.50
     গে
    0.49
    POSITIVE LOGITS
    Dum
    0.73
     Dum
    0.68
    lum
    0.68
    Lum
    0.67
    ptious
    0.66
     Lum
    0.64
    bersome
    0.63
     LUM
    0.61
     lum
    0.60
    blings
    0.60
    Activations Density 0.052%

    No Known Activations