© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235522
    Prev
    Next
    INDEX
    Explanations

    inauguration or start of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    тивних
    0.52
    半分
    0.46
     ক্ষয়ক্ষতি
    0.46
    ワ
    0.46
    盏
    0.43
    Half
    0.42
     веществ
    0.42
     Kč
    0.42
     ምን
    0.41
    𒁉
    0.41
    POSITIVE LOGITS
     presidente
    0.55
     Presidente
    0.50
     اعتق
    0.50
     inició
    0.49
     trabajador
    0.48
     salga
    0.48
     apoyo
    0.47
     inaug
    0.47
     acredit
    0.46
     exercer
    0.46
    Activations Density 0.001%

    No Known Activations