© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108496
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    Not in Any Lists

    No Comments

    Negative Logits
    护士
    -0.91
    ıldız
    -0.90
     زيت
    -0.85
     frequentemente
    -0.84
     Headache
    -0.82
    ництво
    -0.82
    foreach
    -0.81
     wodurch
    -0.80
     worauf
    -0.79
    繖
    -0.79
    POSITIVE LOGITS
     attention
    1.48
     on
    1.29
     more
    1.15
     atención
    1.11
     efforts
    1.08
     solely
    1.05
     Aufmerksamkeit
    1.04
     energies
    1.00
     primarily
    0.98
    Attention
    0.97
    Activations Density 0.014%

    No Known Activations