© 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. 115610
    Prev
    Next
    INDEX
    Explanations

    audio equipment and electronics

    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
     argumentos
    -0.77
    kulum
    -0.77
    timento
    -0.73
    CGPoint
    -0.69
    mts
    -0.69
     foi
    -0.68
    uesa
    -0.68
    ORAGE
    -0.68
    牢
    -0.67
    ult
    -0.67
    POSITIVE LOGITS
     receiver
    1.61
     receivers
    1.52
     amplifier
    1.52
     Receiver
    1.46
     amplifiers
    1.37
    receiver
    1.28
     amp
    1.25
     amps
    1.23
     preamp
    1.22
     Amplifier
    1.16
    Activations Density 0.009%

    No Known Activations