© 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. 31-GEMMASCOPE-2-RES-262K
    7. 108015
    Prev
    Next
    INDEX
    Explanations

    feature, clearly, prevent, strong, gap

    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_31_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
    㳡
    0.45
    XPATH
    0.43
    白的
    0.42
    ARIOS
    0.42
    INFRINGEMENT
    0.41
     defam
    0.41
     especiales
    0.41
     vías
    0.41
    ছে
    0.40
     fitter
    0.40
    POSITIVE LOGITS
    ll
    0.55
    ature
    0.54
    isa
    0.53
    es
    0.52
     ફ
    0.52
    os
    0.51
     THE
    0.51
    it
    0.50
    this
    0.50
    ation
    0.50
    Activations Density 0.004%

    No Known Activations