© 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. 42198
    Prev
    Next
    INDEX
    Explanations

    network structures

    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
    보
    0.43
     tov
    0.43
     бо
    0.43
    BAY
    0.43
     hany
    0.41
    ほか
    0.41
    ン
    0.41
    シュ
    0.40
     c
    0.40
     إلا
    0.40
    POSITIVE LOGITS
     বাড়ীতে
    0.47
    
    0.47
    নিজ
    0.45
    ত্তা
    0.44
     utiliser
    0.44
     кантип
    0.43
    ersonal
    0.42
     conscient
    0.42
     trabajar
    0.41
     Pierws
    0.41
    Activations Density 0.010%

    No Known Activations