© 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. 2594
    Prev
    Next
    INDEX
    Explanations

    materials and classifications

    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
    chr
    -0.88
     apparence
    -0.84
     personnage
    -0.81
     adresse
    -0.80
     financi
    -0.79
     homme
    -0.79
     fous
    -0.78
     fó
    -0.77
     bev
    -0.75
     profili
    -0.75
    POSITIVE LOGITS
     grade
    0.92
    Grade
    0.77
    royd
    0.76
    kmeans
    0.75
    AIS
    0.75
    grade
    0.73
     AIS
    0.71
    SR
    0.71
     Milky
    0.70
     நில
    0.70
    Activations Density 0.017%

    No Known Activations