© 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. 60068
    Prev
    Next
    INDEX
    Explanations

    individual heterogeneity, solving armed robbery

    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
    дона
    -0.77
    OST
    -0.75
    🤑
    -0.75
    viem
    -0.74
     propriety
    -0.73
    nego
    -0.72
    jét
    -0.72
    dymyr
    -0.72
    당
    -0.71
    ले
    -0.70
    POSITIVE LOGITS
     shock
    1.02
    shock
    0.94
     Shock
    0.91
     calibrated
    0.88
     solving
    0.88
     solve
    0.88
     shocks
    0.85
    liza
    0.82
     today
    0.82
     agents
    0.81
    Activations Density 0.018%

    No Known Activations