© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37905
    Prev
    Next
    INDEX
    Explanations

    radio frequency and channels

    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
    école
    -0.84
    φα
    -0.83
    vms
    -0.82
    ƽ
    -0.80
     PSV
    -0.80
     bình
    -0.79
    orro
    -0.79
    glDisable
    -0.79
    ubwa
    -0.77
     GIP
    -0.76
    POSITIVE LOGITS
     frequency
    2.17
     frequencies
    2.14
     channel
    1.95
    frequency
    1.84
    Frequency
    1.71
     channels
    1.69
     band
    1.66
     Frequency
    1.62
    frequencies
    1.56
    channel
    1.53
    Activations Density 0.085%

    No Known Activations