© 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. 206080
    Prev
    Next
    INDEX
    Explanations

    words and their continuations

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

    questions and financial terms

    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
    最终
    0.49
    scale
    0.45
    م
    0.45
    рующих
    0.44
    当时的
    0.42
    It
    0.41
     তৎকালীন
    0.41
     It
    0.40
    Wy
    0.40
    Cleveland
    0.40
    POSITIVE LOGITS
     กด
    0.60
     upotre
    0.57
     strany
    0.54
    ഗ
    0.53
    emailer
    0.52
    嚷
    0.51
     чисто
    0.48
    administ
    0.48
    ufen
    0.47
     elektron
    0.47
    Activations Density 0.000%

    No Known Activations