© 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. 32205
    Prev
    Next
    INDEX
    Explanations

    sports scores and points

    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
    astron
    -0.76
     APPRO
    -0.75
    uccino
    -0.74
     Byp
    -0.74
    Industry
    -0.74
    undidad
    -0.73
     linken
    -0.73
     cheveux
    -0.73
    Approximately
    -0.71
    ícola
    -0.71
    POSITIVE LOGITS
     serve
    1.13
     side
    1.08
     Side
    1.07
     sided
    1.05
     service
    1.00
     winners
    1.00
     kills
    0.99
     kill
    0.98
     serves
    0.96
     points
    0.93
    Activations Density 0.001%

    No Known Activations