© 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. 35898
    Prev
    Next
    INDEX
    Explanations

    time and data structures

    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
     definitively
    -2.80
     convincingly
    -2.78
     disregarding
    -2.75
     enlightening
    -2.75
     marginally
    -2.75
     grossly
    -2.72
     hampered
    -2.70
     relentlessly
    -2.67
     comprehensively
    -2.63
     encompassed
    -2.63
    POSITIVE LOGITS
    –)
    1.36
    )–
    1.23
     semua
    1.11
     '}
    1.11
     💕
    1.10
     '!
    1.09
     стоко
    1.07
     pintu
    1.05
     Ș
    1.05
     🥰
    1.03
    Activations Density 70.837%

    No Known Activations