© 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. 41-GEMMASCOPE-2-RES-262K
    7. 169
    Prev
    Next
    INDEX
    Explanations

    en- prefix

    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_all/layer_41_width_262k_l0_big
    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
    ាប
    0.59
    鵃
    0.53
    accessToken
    0.53
    <unused1084>
    0.52
     ລັບ
    0.51
    <unused1647>
    0.50
    <unused492>
    0.50
    ณา
    0.49
    <unused311>
    0.49
    <unused514>
    0.49
    POSITIVE LOGITS
     En
    1.02
     en
    0.94
    En
    0.88
     Enzo
    0.64
     enl
    0.64
     EN
    0.63
     Enrique
    0.63
     Encore
    0.60
     ens
    0.57
     Enrico
    0.55
    Activations Density 0.016%

    No Known Activations