© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59626
    Prev
    Next
    INDEX
    Explanations

    infrared remote control

    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
    einander
    -0.86
    colm
    -0.84
    utek
    -0.82
    كمة
    -0.81
    rugated
    -0.77
    quill
    -0.77
    rač
    -0.76
    千万
    -0.74
     사이
    -0.73
    capaian
    -0.73
    POSITIVE LOGITS
     IR
    1.50
    IR
    1.16
     infrared
    0.96
     CEC
    0.94
     IRS
    0.87
     cec
    0.87
    irma
    0.86
     Pronto
    0.85
     TVs
    0.85
     infrar
    0.85
    Activations Density 0.013%

    No Known Activations