© 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. 22-GEMMASCOPE-RES-131K
    7. 40037
    Prev
    Next
    INDEX
    Explanations

    abstract nouns

    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
    会有
    -1.04
     queste
    -1.00
     nhưng
    -0.99
    这
    -0.98
     bao
    -0.97
    會有
    -0.96
     estar
    -0.93
     alcune
    -0.92
    ਗ਼
    -0.91
     <>",
    -0.91
    POSITIVE LOGITS
     itself
    1.70
     actually
    1.38
     непосредственно
    1.37
     actual
    1.29
     himself
    1.26
     directly
    1.23
    本身
    1.21
     selve
    1.20
     themselves
    1.13
     invece
    1.12
    Activations Density 0.100%

    No Known Activations