© 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. 13664
    Prev
    Next
    INDEX
    Explanations

    exploration and journeys

    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
     Tolst
    0.64
     Idiot
    0.62
     こんな
    0.61
     Related
    0.61
     Selain
    0.61
     Organization
    0.60
    _*
    0.60
     ایالات
    0.60
     Subscriber
    0.59
     Truly
    0.59
    POSITIVE LOGITS
    芯
    0.54
    崴
    0.52
    Future
    0.49
     marginalised
    0.49
    cées
    0.49
    俣
    0.48
    码
    0.48
    üe
    0.47
     seams
    0.47
    FUTURE
    0.46
    Activations Density 0.063%

    No Known Activations