© 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. 48353
    Prev
    Next
    INDEX
    Explanations

    Okay, generative preface

    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
    5
    0.53
    REM
    0.44
     )
    0.44
    BC
    0.43
    4
    0.43
    c
    0.42
    dub
    0.42
    7
    0.42
     denominado
    0.42
    p
    0.41
    POSITIVE LOGITS
    ండి
    0.50
     الرابعه
    0.48
    ائص
    0.46
     बेहतरीन
    0.46
    㪇
    0.46
    飏
    0.46
     journalistic
    0.46
    制造商
    0.44
    lowing
    0.43
    춰
    0.43
    Activations Density 0.002%

    No Known Activations