© 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. 86264
    Prev
    Next
    INDEX
    Explanations

    nations or other foreign countries

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

    describes abstract properties and relationships

    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
     boş
    0.48
     drew
    0.47
     były
    0.46
    andı
    0.44
     Maulana
    0.44
     vazio
    0.44
    DisplayText
    0.44
    辕
    0.43
     başlat
    0.43
     Volodymyr
    0.43
    POSITIVE LOGITS
     homogeneous
    0.66
     homogenous
    0.58
     normative
    0.54
     adaptive
    0.54
     monotonicity
    0.54
     interdependence
    0.52
     interdependent
    0.51
     benthic
    0.50
     heterogeneous
    0.49
     autonomy
    0.49
    Activations Density 0.000%

    No Known Activations