© 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. 58115
    Prev
    Next
    INDEX
    Explanations

    survival game show terms

    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
     skaters
    -1.02
     Prose
    -0.78
    ソース
    -0.77
     Maitland
    -0.75
    濕
    -0.74
    canakan
    -0.73
    瘙
    -0.73
     пові
    -0.72
    メッセージ
    -0.72
    ランク
    -0.72
    POSITIVE LOGITS
    Survivor
    1.48
     Survivor
    1.41
     tribe
    1.27
    Tribal
    1.16
     Tribal
    1.08
     tribal
    1.07
     immunity
    1.02
    tribal
    0.99
     tribes
    0.97
     idol
    0.94
    Activations Density 0.008%

    No Known Activations