© 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. 93923
    Prev
    Next
    INDEX
    Explanations

    radio station frequencies or MHz

    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
     News
    -0.91
     news
    -0.91
     morning
    -0.84
     afternoon
    -0.82
    News
    -0.80
    غاز
    -0.73
    Ito
    -0.71
     Ito
    -0.68
     entertainment
    -0.66
     Trading
    -0.66
    POSITIVE LOGITS
     volunteer
    0.89
    Volunteer
    0.88
    volunteer
    0.83
     Volunteer
    0.80
    的区别
    0.79
     presenters
    0.79
     community
    0.77
     WSU
    0.76
     België
    0.75
    ⊲
    0.75
    Activations Density 0.037%

    No Known Activations