© 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. 14539
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    嫨
    0.56
     ది
    0.54
    omani
    0.54
    გუფი
    0.54
     chuyện
    0.53
    soever
    0.53
     Hg
    0.53
    atorias
    0.53
     Hispanics
    0.52
     perceptible
    0.52
    POSITIVE LOGITS
    setMax
    0.54
    ]$-
    0.53
     destinat
    0.53
     grafting
    0.52
    慎
    0.52
     oblic
    0.51
     voorbeeld
    0.50
    essero
    0.50
    الف
    0.50
     options
    0.49
    Activations Density 0.000%

    No Known Activations