© 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-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 302
    Prev
    Next
    INDEX
    Explanations

    UnitedMethod Used: 1Reason: MAX_ACTIVATING_TOKENS consistently relate to the word "United"

    np_max-act-logits · gemini-2.5-flash-lite

    United States

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mirar
    0.55
    ಲೋ
    0.54
    avelmente
    0.53
     IPython
    0.53
    ablemente
    0.52
    оны
    0.52
     puberty
    0.50
    練
    0.49
     decent
    0.49
     সৈয়দ
    0.48
    POSITIVE LOGITS
    States
    0.66
     الدول
    0.64
     States
    0.63
     U
    0.62
    prising
    0.62
    sonian
    0.62
    क्‍त
    0.60
    rologist
    0.60
    どん
    0.59
    ILITY
    0.59
    Activations Density 0.414%

    No Known Activations