© 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. 99537
    Prev
    Next
    INDEX
    Explanations

    avoiding detection

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

    The neuron detects words and phrases that refer to hiding, evading, or avoiding detection.

    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
    randall
    -0.89
    ijão
    -0.88
    carpus
    -0.88
     insults
    -0.85
     enigmatic
    -0.82
    隐隐
    -0.81
    Exclusive
    -0.81
    zia
    -0.80
    dimer
    -0.79
    sometimes
    -0.78
    POSITIVE LOGITS
     detection
    2.34
    バレ
    1.91
     detected
    1.85
    detection
    1.85
     discovered
    1.84
     detectable
    1.84
     Detection
    1.76
     noticed
    1.69
    Detection
    1.64
     conspicuous
    1.61
    Activations Density 0.053%

    No Known Activations