© 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. 116073
    Prev
    Next
    INDEX
    Explanations

    spoken word

    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
     follows
    -0.75
    го
    -0.72
    주의
    -0.71
     Whipple
    -0.71
     Hearing
    -0.68
     sata
    -0.68
    audio
    -0.68
    ско
    -0.66
     inteiro
    -0.66
    tac
    -0.66
    POSITIVE LOGITS
     speak
    4.91
     speaking
    4.50
     spoke
    3.81
     speaks
    3.67
    speak
    3.48
     talking
    3.33
     talk
    3.30
     Speak
    3.27
    speaking
    3.23
    Speak
    3.23
    Activations Density 0.050%

    No Known Activations