© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86965
    Prev
    Next
    INDEX
    Explanations

    defeat against opposing 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
     VICT
    -0.93
     victory
    -0.90
    ɝ
    -0.84
    ندن
    -0.83
     triumph
    -0.81
     länge
    -0.80
    arned
    -0.78
    argp
    -0.78
    bigliamento
    -0.78
    ugt
    -0.77
    POSITIVE LOGITS
     loss
    2.14
    Loss
    1.84
     losses
    1.82
    loss
    1.79
     Loss
    1.74
    LOSS
    1.61
     Losses
    1.52
    losses
    1.43
     LOSS
    1.34
     lost
    1.30
    Activations Density 0.019%

    No Known Activations