© 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. 85931
    Prev
    Next
    INDEX
    Explanations

    initially or first language

    np_acts-logits-general · gemini-2.5-flash-lite

    initial state or beginning

    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
    Not in Any Lists

    No Comments

    Negative Logits
    的這個
    0.57
     этом
    0.54
    也會
    0.52
     tomto
    0.51
     referrerpolicy
    0.50
     mencionar
    0.48
     sentimento
    0.48
    ט
    0.48
     smelly
    0.48
     这个
    0.47
    POSITIVE LOGITS
     initially
    0.53
     сначала
    0.52
     முதலில்
    0.51
     zunächst
    0.48
    Initially
    0.47
     －
    0.46
     पहला
    0.46
     처음
    0.46
     begins
    0.45
     initial
    0.44
    Activations Density 0.006%

    No Known Activations