© 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. 72716
    Prev
    Next
    INDEX
    Explanations

    cause and consequence

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

    both excellent and powerful

    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
     골
    0.53
    lád
    0.49
    jeni
    0.49
    tsó
    0.47
    lichkeit
    0.47
    ladı
    0.47
     已
    0.47
    klad
    0.46
    肓
    0.46
    pcs
    0.46
    POSITIVE LOGITS
     grants
    0.45
     dith
    0.44
    Wheat
    0.43
    তাদের
    0.43
    ඈ
    0.41
     waiters
    0.40
     tensions
    0.39
    LOUISE
    0.38
     loans
    0.37
    ত্যাশিত
    0.37
    Activations Density 0.003%

    No Known Activations