© 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. 64199
    Prev
    Next
    INDEX
    Explanations

    trophy awards championship

    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
    ㎎
    -0.82
    kem
    -0.80
     famí
    -0.76
    tunnel
    -0.73
    vember
    -0.72
     Sorte
    -0.72
    líben
    -0.69
     Caul
    -0.69
    ชี
    -0.68
     Tagged
    -0.67
    POSITIVE LOGITS
     trophy
    4.00
     trophies
    3.81
    trophy
    2.69
     Trophy
    2.56
     medals
    2.39
     awards
    2.23
     Trop
    2.22
    trop
    2.16
     trofeo
    2.11
     medal
    2.03
    Activations Density 0.024%

    No Known Activations