© 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. 47979
    Prev
    Next
    INDEX
    Explanations

    say or voice

    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
    밖
    -0.92
     uniquement
    -0.90
     disponib
    -0.88
    áctica
    -0.86
    mpel
    -0.80
     vif
    -0.79
    يفة
    -0.79
    シルバー
    -0.79
     kapture
    -0.77
    מית
    -0.75
    POSITIVE LOGITS
     say
    3.25
    say
    2.69
     voice
    2.47
    Say
    2.41
     input
    2.34
     influence
    2.22
     Say
    2.17
     SAY
    2.13
    voice
    1.89
    SAY
    1.88
    Activations Density 0.025%

    No Known Activations