© 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. 80884
    Prev
    Next
    INDEX
    Explanations

    communication and language use

    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
     unconditionally
    -0.84
     tanım
    -0.80
     ευ
    -0.75
     apabila
    -0.75
     ście
    -0.73
     arbets
    -0.73
     Explanation
    -0.71
    ād
    -0.70
     unanimous
    -0.69
     directamente
    -0.68
    POSITIVE LOGITS
     speaker
    1.27
     message
    1.13
     communication
    1.09
    ENCODING
    1.09
    encode
    1.09
     encoding
    1.09
     thoughts
    1.07
    Thoughts
    1.02
     Speaker
    1.02
     speakers
    1.02
    Activations Density 0.052%

    No Known Activations