© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59608
    Prev
    Next
    INDEX
    Explanations

    college sports teams

    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
     reducing
    -0.74
     problemática
    -0.68
     problems
    -0.68
     adulti
    -0.67
    Ȟ
    -0.65
     lebens
    -0.65
    astas
    -0.65
    urr
    -0.64
    toByteArray
    -0.63
    zegorz
    -0.63
    POSITIVE LOGITS
     women
    2.16
     football
    2.11
     basketball
    2.06
     men
    1.98
     baseball
    1.93
     soccer
    1.67
     softball
    1.63
     volleyball
    1.59
     hockey
    1.52
     rugby
    1.47
    Activations Density 0.067%

    No Known Activations