© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32571
    Prev
    Next
    INDEX
    Explanations

    hotlines and support services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nécess
    0.61
     dictated
    0.58
    6
    0.54
     progrès
    0.50
    ﺔ
    0.50
     mouvements
    0.50
    ᱔
    0.50
     świad
    0.50
    ﻊ
    0.49
     posuere
    0.49
    POSITIVE LOGITS
    攽
    0.51
    ומי
    0.50
    atkan
    0.47
    inna
    0.46
    იდან
    0.44
    నా
    0.43
     書い
    0.43
    ট
    0.42
     I
    0.41
    ტის
    0.41
    Activations Density 0.005%

    No Known Activations