© 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. 73515
    Prev
    Next
    INDEX
    Explanations

    international code snippets

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

    The neuron primarily detects the end of a block comment delimiter (the “*/” sequence).

    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
    /**
    -1.46
    ;
    -1.11
    providedIn
    -1.10
     this
    -1.09
     only
    -1.09
     it
    -1.04
    /**
    -0.98
     being
    -0.96
    currentThread
    -0.96
     extends
    -0.94
    POSITIVE LOGITS
    ↵
    1.16
     ของ
    1.05
    ventude
    1.04
     เปิด
    1.04
    луйста
    1.04
    Hercules
    1.02
    úan
    0.99
    וקה
    0.98
    Chassis
    0.98
    ליך
    0.97
    Activations Density 0.007%

    No Known Activations