© 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. 89857
    Prev
    Next
    INDEX
    Explanations

    frequency units (Hz, kHz, 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
     horário
    -0.80
     swo
    -0.73
    mpa
    -0.73
     flagrant
    -0.72
    jwa
    -0.72
     说
    -0.71
     Gitar
    -0.70
    Vars
    -0.70
    woll
    -0.69
    cahontas
    -0.69
    POSITIVE LOGITS
     frequency
    1.31
     frequencies
    1.24
     high
    1.09
    kHz
    0.89
     higher
    0.88
     Kil
    0.87
    kh
    0.85
    高
    0.85
     LF
    0.83
     kHz
    0.81
    Activations Density 0.067%

    No Known Activations