© 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. 129052
    Prev
    Next
    INDEX
    Explanations

    sociedades, familias, entities, society

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

    conference, segments, data analysis, constraints, waves, born, Marxist

    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
    ద్ర
    0.49
    сторо
    0.47
    мал
    0.47
    द्रा
    0.46
    שׁ
    0.46
     Protocol
    0.45
    ג
    0.45
    зо
    0.45
    ਦ
    0.44
    тра
    0.43
    POSITIVE LOGITS
    ugging
    0.52
     fins
    0.51
     المجتمع
    0.51
     sociedades
    0.50
     actualizado
    0.50
     entidades
    0.49
     familias
    0.48
     maximizes
    0.48
    ’
    0.48
     sociedade
    0.48
    Activations Density 0.002%

    No Known Activations