© 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. 50351
    Prev
    Next
    INDEX
    Explanations

    scope, trace, waveform analysis

    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
    bidity
    -1.05
    anyahu
    -0.82
     SwitchCompat
    -0.81
    atorship
    -0.79
    놨
    -0.76
     macron
    -0.75
    alda
    -0.74
     RDC
    -0.74
     cooks
    -0.73
    Τα
    -0.73
    POSITIVE LOGITS
     trace
    1.00
     acquisitions
    0.94
     probe
    0.93
     waveform
    0.90
     Trace
    0.90
     probes
    0.90
     acquisition
    0.88
    Acquisition
    0.88
     Probe
    0.86
     waveforms
    0.86
    Activations Density 0.010%

    No Known Activations