© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79491
    Prev
    Next
    INDEX
    Explanations

    sending your article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Zij
    -0.81
    chelsea
    -0.75
    ahua
    -0.74
    siy
    -0.74
    Redraw
    -0.73
    luka
    -0.72
     význam
    -0.72
    Asser
    -0.71
    laria
    -0.71
    buka
    -0.71
    POSITIVE LOGITS
    собен
    0.73
    Ϻ
    0.73
    ≖
    0.72
    widget
    0.69
     establishing
    0.69
     utterly
    0.67
     blatantly
    0.66
     establishes
    0.66
    NotSupported
    0.66
     using
    0.65
    Activations Density 0.084%

    No Known Activations