© 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. 78924
    Prev
    Next
    INDEX
    Explanations

    tree and graph traversal

    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
     المفت
    -0.75
    magitan
    -0.74
     smokes
    -0.68
    rump
    -0.67
    五六
    -0.66
    inobu
    -0.66
     debris
    -0.65
    ulture
    -0.64
     Тан
    -0.64
     Refugees
    -0.64
    POSITIVE LOGITS
     traverse
    4.41
     traversal
    4.16
    traverse
    3.81
     Traverse
    3.69
     traversing
    3.64
     traversed
    3.58
    Traverse
    3.50
     traverses
    3.48
     travers
    3.30
    traversal
    3.17
    Activations Density 0.146%

    No Known Activations