© 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. 62791
    Prev
    Next
    INDEX
    Explanations

    Wells Fargo and Road

    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
    stod
    -0.83
     Bella
    -0.76
     бри
    -0.76
     PAT
    -0.74
     куби
    -0.72
     Paddy
    -0.72
    amili
    -0.70
     threatening
    -0.70
     unserer
    -0.68
     Chuan
    -0.68
    POSITIVE LOGITS
     Fargo
    1.26
     Wells
    1.00
    Wells
    0.96
     Wach
    0.87
    ческого
    0.79
    akala
    0.78
    匐
    0.75
     wartości
    0.74
    场比赛
    0.74
     Alfalfa
    0.74
    Activations Density 0.019%

    No Known Activations