© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    Logcat output

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

    The neuron strongly activates on Android debug‐logging calls (e.g. “Log.d(…)” and the surrounding punctuation).

    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
    Astr
    -0.87
    搅
    -0.82
     Laid
    -0.80
     Bracken
    -0.75
    textwidth
    -0.72
    openqa
    -0.72
    ItemLayout
    -0.71
    öra
    -0.71
    ător
    -0.71
    rauch
    -0.71
    POSITIVE LOGITS
    cat
    1.45
     cat
    1.02
     Cat
    0.95
    Cat
    0.91
     Log
    0.84
    w
    0.82
    我真的
    0.82
    Verbose
    0.81
    Log
    0.80
    wtf
    0.79
    Activations Density 0.069%

    No Known Activations