© 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. 199125
    Prev
    Next
    INDEX
    Explanations

    quantities and progress

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

    explaining how things develop

    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
     lắc
    0.49
     senses
    0.42
    ತರ
    0.42
    ートル
    0.41
     examiners
    0.40
     psychologists
    0.40
     カード
    0.40
    懾
    0.40
     FIELD
    0.40
    WEEK
    0.40
    POSITIVE LOGITS
    larger
    0.46
    publik
    0.46
     producir
    0.44
     expon
    0.44
    produktion
    0.44
    estabelecimento
    0.43
     działal
    0.43
     nast
    0.43
     produk
    0.43
    ഒരു
    0.43
    Activations Density 0.000%

    No Known Activations