© 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. 60305
    Prev
    Next
    INDEX
    Explanations

    radio announcer 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
    SUPPORT
    -0.73
    appui
    -0.72
    CIM
    -0.72
    Bor
    -0.72
    Td
    -0.71
    Tint
    -0.69
    uaa
    -0.69
    BOR
    -0.69
    Bat
    -0.69
    去年
    -0.69
    POSITIVE LOGITS
     radio
    1.34
     Radio
    1.13
     announcer
    1.05
     RADIO
    1.02
    radio
    0.96
     reads
    0.89
     copy
    0.88
     voice
    0.86
     narration
    0.84
     радио
    0.84
    Activations Density 0.024%

    No Known Activations