© 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. 58397
    Prev
    Next
    INDEX
    Explanations

    basketball league 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
     Croydon
    -0.85
    regler
    -0.81
    cua
    -0.79
    amino
    -0.75
    threading
    -0.75
     ブーツ
    -0.73
    kuwa
    -0.73
    tracing
    -0.73
    rehensible
    -0.72
    ztyn
    -0.71
    POSITIVE LOGITS
     hoops
    0.92
     baskets
    0.89
     basket
    0.81
     פֿ
    0.79
     operational
    0.78
     FIBA
    0.76
     Coimbra
    0.76
    operational
    0.75
     Üniversitesi
    0.74
    Ops
    0.74
    Activations Density 0.040%

    No Known Activations