© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69080
    Prev
    Next
    INDEX
    Explanations

    foreign places or abroad

    np_acts-logits-general · gemini-2.5-flash-lite

    worldwide locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    Constit
    0.43
    噌
    0.41
    нение
    0.40
     결방
    0.39
    ClkInitStruct
    0.39
    ेश्वर
    0.39
    ലാണ്
    0.38
    Constitution
    0.38
    报考
    0.38
    탉
    0.38
    POSITIVE LOGITS
     overseas
    1.24
    国外
    1.23
     Europe
    1.23
     elsewhere
    1.21
     worldwide
    1.19
     abroad
    1.19
     यूरोप
    1.13
     اروپا
    1.13
     विदेशों
    1.13
     European
    1.12
    Activations Density 1.022%

    No Known Activations