© 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. 229481
    Prev
    Next
    INDEX
    Explanations

    numbers and words

    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
    g
    0.55
     onus
    0.53
    financing
    0.53
     neutrophils
    0.52
    gir
    0.49
     όταν
    0.47
    funds
    0.47
     Emirates
    0.46
    ga
    0.45
     financing
    0.45
    POSITIVE LOGITS
     каждого
    0.61
     每个
    0.59
    ция
    0.52
    歙
    0.51
    各地
    0.50
    每个
    0.50
    之间
    0.50
     Each
    0.49
    ずつ
    0.49
    之間
    0.48
    Activations Density 0.000%

    No Known Activations