© 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. 113104
    Prev
    Next
    INDEX
    Explanations

    there were, fire hydrants

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

    proper nouns and specific terms

    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
     помещение
    0.55
     ventanas
    0.51
     acessórios
    0.50
     estás
    0.48
     помещения
    0.47
     здание
    0.47
     одежда
    0.46
     요
    0.45
     fábrica
    0.45
    Gracias
    0.45
    POSITIVE LOGITS
     disputed
    0.48
    statistik
    0.48
    nabla
    0.46
    zigen
    0.46
     parallel
    0.44
     Hagen
    0.44
    klady
    0.43
     statist
    0.43
     roads
    0.43
     highways
    0.43
    Activations Density 0.000%

    No Known Activations