© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40366
    Prev
    Next
    INDEX
    Explanations

    all or every documentation

    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
    that
    0.44
     that
    0.41
     voorkomen
    0.40
    それを
    0.39
    𒋫
    0.39
     που
    0.38
    ților
    0.37
    που
    0.37
     мог
    0.37
     That
    0.37
    POSITIVE LOGITS
     તમામ
    0.50
     każdej
    0.48
    每个
    0.46
     દરેક
    0.46
     सभी
    0.46
     প্রতিটি
    0.46
     ყველა
    0.46
     każdego
    0.45
    <table>
    0.45
    Issledovatel
    0.44
    Activations Density 0.047%

    No Known Activations