© 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. 206756
    Prev
    Next
    INDEX
    Explanations

    Portugal Eritrea Quebec

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

    specific named entities and concepts

    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
    사는
    0.52
    校
    0.51
    лів
    0.48
    їв
    0.47
    지는
    0.45
    さを
    0.45
    서는
    0.45
    라는
    0.45
    비를
    0.44
    야
    0.44
    POSITIVE LOGITS
     Portugal
    0.59
     Eritrea
    0.56
     Quebec
    0.55
     Campeonato
    0.54
     wichtiger
    0.54
    Portugal
    0.54
     AutoML
    0.54
     Ethiopia
    0.53
     Burkina
    0.53
    দৌ
    0.52
    Activations Density 0.000%

    No Known Activations