© 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. 34-GEMMASCOPE-RES-131K
    7. 73737
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
     six
    -1.17
     five
    -1.16
     two
    -1.02
     three
    -0.98
    してた
    -0.97
    してる
    -0.91
     temp
    -0.90
    してます
    -0.89
     at
    -0.89
     or
    -0.89
    POSITIVE LOGITS
    actually
    1.12
    mediately
    1.07
     mutfak
    1.06
    ή
    1.02
     também
    0.96
     Wij
    0.96
     ぼ
    0.95
    density
    0.93
    лович
    0.92
    ことも
    0.91
    Activations Density 0.001%

    No Known Activations