© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68503
    Prev
    Next
    INDEX
    Explanations

    project, list, and calendar objects

    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_22/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
    ילות
    -1.13
    citation
    -1.02
    raktion
    -0.98
    tissimi
    -0.94
    ringes
    -0.92
    Hechos
    -0.90
    quait
    -0.88
    섹
    -0.88
     aquellas
    -0.88
    chaic
    -0.88
    POSITIVE LOGITS
     itself
    1.16
     management
    0.96
     themselves
    0.94
     selbst
    0.91
     עצ
    0.91
     maîtres
    0.85
    𝐿
    0.84
     information
    0.84
     kesk
    0.84
    及其
    0.83
    Activations Density 0.019%

    No Known Activations