© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10160
    Prev
    Next
    INDEX
    Explanations

    cultural context and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    не
    0.60
    اس
    0.58
     Micros
    0.57
    YY
    0.56
     그대로
    0.56
    Ν
    0.56
    結構
    0.55
    לה
    0.53
    riften
    0.53
    untansi
    0.53
    POSITIVE LOGITS
    Cult
    1.07
     Cultural
    1.04
     Cult
    1.00
    Cultural
    1.00
     Kult
    0.89
     культур
    0.86
     culturais
    0.84
     cultural
    0.83
    ivation
    0.81
     куль
    0.79
    Activations Density 0.069%

    No Known Activations