© 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. 65063
    Prev
    Next
    INDEX
    Explanations

    sports discussion phrases

    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
     VIS
    -0.90
    sw
    -0.83
     UPDATED
    -0.78
     arrep
    -0.77
    TypeName
    -0.76
     players
    -0.75
    NFL
    -0.75
    locker
    -0.75
    pan
    -0.74
     TR
    -0.74
    POSITIVE LOGITS
     Specify
    0.90
     our
    0.89
     specify
    0.83
    ӓ
    0.81
     μας
    0.79
     zároveň
    0.77
     Landschaft
    0.77
     Máy
    0.77
    DDG
    0.76
    今の
    0.75
    Activations Density 0.006%

    No Known Activations