© 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. 208105
    Prev
    Next
    INDEX
    Explanations

    compound words and constructions

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

    make or analysis

    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
    ק
    0.64
    データ
    0.59
    アー
    0.52
    옇
    0.50
     vivir
    0.49
    ق
    0.49
    А
    0.49
    amaan
    0.47
    아
    0.46
    データを
    0.46
    POSITIVE LOGITS
     trägt
    0.50
     gördüğünüz
    0.47
     ബ്രിട്ട
    0.46
     attributing
    0.46
     Fridge
    0.44
     связана
    0.44
    水的
    0.44
    见的
    0.44
     الشمس
    0.44
    边的
    0.43
    Activations Density 0.000%

    No Known Activations