© 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. 36369
    Prev
    Next
    INDEX
    Explanations

    Roman numeral II

    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
    ↵↵
    -3.69
    0
    -2.70
     enormous
    -2.58
    :
    -2.58
     exuberant
    -2.47
    ください
    -2.23
     glamorous
    -2.13
     какой
    -2.09
    lgari
    -2.08
     wicked
    -2.05
    POSITIVE LOGITS
    
    2.84
     was
    2.67
     continúas
    2.58
    h
    2.55
    鹛
    2.52
    釤
    2.36
    e
    2.34
    u
    2.33
    もの
    2.31
     alamu
    2.22
    Activations Density 0.024%

    No Known Activations