© 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. 34-GEMMASCOPE-RES-131K
    4. 110913
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation

    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_34/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
     letter
    -0.92
     letters
    -0.91
    }}:
    -0.80
     numeric
    -0.75
    木材
    -0.75
     vertebrate
    -0.74
     prefix
    -0.74
    anske
    -0.73
     catastrophic
    -0.72
    letter
    -0.72
    POSITIVE LOGITS
    symbols
    1.40
     symbols
    1.36
     punctuation
    1.34
    Symbols
    1.16
     Symbols
    1.12
    Pun
    1.12
    syms
    1.08
     symbol
    1.06
     punctu
    1.06
    SYMBOL
    1.05
    Activations Density 0.055%

    No Known Activations