© 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. 98004
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by new phrases as in talk

    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
     особенно
    -1.07
     etiam
    -1.02
    残念
    -0.95
    especially
    -0.91
    
    -0.90
    のだろう
    -0.86
    是吗
    -0.86
    particularly
    -0.84
     почему
    -0.84
    Soorten
    -0.83
    POSITIVE LOGITS
     talk
    4.41
     Talk
    3.98
    Talk
    3.95
    talk
    3.78
    TALK
    2.64
     TALK
    2.56
     talks
    2.03
     talked
    1.81
     how
    1.80
    talks
    1.80
    Activations Density 0.061%

    No Known Activations