© 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. 78048
    Prev
    Next
    INDEX
    Explanations

    sports club names

    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
    easy
    -1.27
     easy
    -1.14
     ez
    -1.00
     fácil
    -0.97
     vita
    -0.96
    ง่าย
    -0.96
    Easy
    -0.91
     nog
    -0.90
     interpreta
    -0.89
     reconna
    -0.87
    POSITIVE LOGITS
     confirmó
    0.85
     jestem
    0.84
     jessica
    0.84
     Ottawa
    0.83
    kring
    0.82
     strix
    0.81
     vestiges
    0.81
    ([
    0.81
     Warsaw
    0.81
    ciencia
    0.77
    Activations Density 0.025%

    No Known Activations