© 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. 14547
    Prev
    Next
    INDEX
    Explanations

    English places

    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
     Allegheny
    0.75
     Steelers
    0.62
     Mbappe
    0.61
    渝
    0.61
     केरल
    0.60
     Pittsburgh
    0.58
    新宿
    0.58
    蟠
    0.58
     SQLAlchemy
    0.57
    🕋
    0.57
    POSITIVE LOGITS
     Norfolk
    2.69
     Norwich
    2.42
     Suffolk
    2.09
    Nor
    1.63
     Ipswich
    1.63
    Suff
    1.27
     NOR
    1.23
    SUFF
    1.17
    NOR
    1.16
    nor
    1.14
    Activations Density 0.041%

    No Known Activations