© 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. 10-GEMMASCOPE-RES-131K
    7. 70561
    Prev
    Next
    INDEX
    Explanations

    cold war strategy and games

    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_10/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
    biker
    -2.05
    ieR
    -1.90
    瑒
    -1.88
    orghini
    -1.86
     this
    -1.73
    dali
    -1.71
     estrateg
    -1.70
     encantado
    -1.67
    casco
    -1.66
     berücksich
    -1.66
    POSITIVE LOGITS
    c
    2.22
    1
    2.20
    0
    2.16
    3
    2.02
    R
    1.98
    8
    1.92
    V
    1.91
    H
    1.91
    id
    1.89
    m
    1.88
    Activations Density 0.009%

    No Known Activations