© 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. 60006
    Prev
    Next
    INDEX
    Explanations

    specific nouns

    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
     if
    -1.50
     since
    -1.38
     each
    -1.14
     persino
    -1.13
     because
    -1.13
     will
    -1.13
     even
    -1.13
    ほうがいい
    -1.10
     pretože
    -1.09
     addirittura
    -1.09
    POSITIVE LOGITS
     usually
    2.42
    usually
    2.42
    often
    1.92
    either
    1.91
     souvent
    1.88
     either
    1.86
     generalmente
    1.86
     обычно
    1.84
     généralement
    1.80
     biasanya
    1.80
    Activations Density 0.454%

    No Known Activations