© 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. 47274
    Prev
    Next
    INDEX
    Explanations

    css, background, opacity, display

    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
    glGen
    -0.99
     공
    -0.89
     cần
    -0.82
     lamenta
    -0.79
    isHidden
    -0.78
    Concluding
    -0.78
    })_{
    -0.76
     Trauer
    -0.76
    château
    -0.74
    cesis
    -0.74
    POSITIVE LOGITS
    transform
    0.83
    டி
    0.83
    BorderStyle
    0.79
    tlement
    0.78
    变
    0.77
    變
    0.77
     переста
    0.75
    背景
    0.74
    eamento
    0.74
     becomes
    0.74
    Activations Density 0.016%

    No Known Activations