© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117284
    Prev
    Next
    INDEX
    Explanations

    shipped and

    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
     socio
    -0.82
     llantas
    -0.77
    HasForeignKey
    -0.74
     Frequent
    -0.73
    ContentAlignment
    -0.72
     ۷
    -0.72
     وغ
    -0.67
    Ь
    -0.67
    tom
    -0.66
     nut
    -0.66
    POSITIVE LOGITS
    alne
    0.74
    yně
    0.73
    宜しくお願い
    0.70
    piele
    0.70
    sumowanie
    0.70
    Azur
    0.70
    ינו
    0.69
    RSC
    0.69
     Majestic
    0.69
     baili
    0.69
    Activations Density 0.001%

    No Known Activations