© 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-65K
    7. 9947
    Prev
    Next
    INDEX
    Explanations

    breakdown, categorized

    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_65k_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
    有一种
    0.45
     mirar
    0.43
     मेरी
    0.41
     campuran
    0.41
    temperatur
    0.40
    ₂)
    0.40
     daß
    0.40
     غذا
    0.40
     Nasıl
    0.40
    dört
    0.40
    POSITIVE LOGITS
    ໊
    0.45
    ://
    0.44
    ⵥ
    0.43
    <table>
    0.42
    ⌔
    0.41
    ;&
    0.41
    ଃ
    0.41
     clés
    0.41
    -$
    0.40
     battles
    0.39
    Activations Density 0.052%

    No Known Activations