© 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. 83032
    Prev
    Next
    INDEX
    Explanations

    audio components and systems

    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
    蛎
    -0.75
    Rhestr
    -0.68
     番目
    -0.67
    ẹp
    -0.66
    insensitive
    -0.66
    choir
    -0.66
     kapturem
    -0.64
     jeżeli
    -0.63
     brauchst
    -0.63
     sonido
    -0.63
    POSITIVE LOGITS
     satellites
    1.12
     входа
    0.87
     multimedia
    0.85
     maig
    0.84
    MEDIA
    0.83
    system
    0.82
    ró
    0.79
     desktop
    0.79
    RMS
    0.79
     Weimar
    0.78
    Activations Density 0.019%

    No Known Activations