© 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. 1127
    Prev
    Next
    INDEX
    Explanations

    cho

    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
    但
    -2.61
     может
    -2.34
    ться
    -2.27
     entice
    -2.22
     только
    -2.08
     как
    -2.06
    ของ
    -2.05
    ﺢ
    -2.02
    ского
    -2.00
     pero
    -1.99
    POSITIVE LOGITS
    0
    2.72
    媜
    2.70
    y
    2.69
    橚
    2.67
    g
    2.66
    亊
    2.64
    各样的
    2.61
    髕
    2.41
    u
    2.38
     апре
    2.34
    Activations Density 0.006%

    No Known Activations