© 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. 34579
    Prev
    Next
    INDEX
    Explanations

    access to tools

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is responding to runs of leading‐whitespace in code (i.e. indentation tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    xec
    -0.69
    arbitrary
    -0.66
     Reb
    -0.65
     Profess
    -0.64
    Monaco
    -0.62
    verde
    -0.62
     Roja
    -0.62
     Technische
    -0.62
     tangential
    -0.60
     בז
    -0.60
    POSITIVE LOGITS
    rowser
    0.80
    Theme
    0.74
    getValues
    0.73
    ieden
    0.72
    ThemeProvider
    0.71
    ội
    0.70
     Winchester
    0.69
     felicidad
    0.69
     याद
    0.68
    nete
    0.68
    Activations Density 0.041%

    No Known Activations