© 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. 40-GEMMASCOPE-2-RES-262K
    7. 100131
    Prev
    Next
    INDEX
    Explanations

    d/do prefixes

    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_40_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
     endanger
    0.40
     fas
    0.40
     fasci
    0.39
    opard
    0.38
     besonder
    0.38
    dessus
    0.37
     片
    0.37
     mir
    0.37
     예정
    0.37
    typicode
    0.36
    POSITIVE LOGITS
     বজ
    0.42
    של
    0.42
    вів
    0.41
    Match
    0.41
     expériences
    0.40
     Pó
    0.39
     आगे
    0.38
    Surf
    0.37
    Мі
    0.37
    𝐯
    0.37
    Activations Density 0.003%

    No Known Activations