© 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. 119244
    Prev
    Next
    INDEX
    Explanations

    differential signal transmission

    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
    IPV
    -0.79
    ComponentName
    -0.77
    haria
    -0.71
    eful
    -0.71
     UHF
    -0.70
    mpy
    -0.69
    Msp
    -0.69
    kowy
    -0.68
    fsm
    -0.68
     ObjectParameter
    -0.68
    POSITIVE LOGITS
     signaling
    0.91
     voting
    0.86
     buses
    0.83
     бу
    0.80
     Signaling
    0.79
     nets
    0.79
     buf
    0.78
    Registered
    0.78
     diffé
    0.75
    izarro
    0.74
    Activations Density 0.037%

    No Known Activations