© 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. 7002
    Prev
    Next
    INDEX
    Explanations

    MIT License, issue, Operation

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

    The neuron fires on HTML italics markup, specifically the opening <i> tag and its contents.

    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
     only
    -0.96
    kelijk
    -0.94
    賄
    -0.87
    ఊ
    -0.87
     posing
    -0.87
    ācijas
    -0.86
     Gewebe
    -0.86
     lounging
    -0.85
    都需要
    -0.85
    廻
    -0.85
    POSITIVE LOGITS
    <b>
    1.49
    </i>
    1.45
    <i>
    1.29
    
    1.05
    "},
    0.94
    }}.
    0.94
    hahahaha
    0.92
    <0xEE>
    0.92
    一股
    0.92
    
    0.91
    Activations Density 0.001%

    No Known Activations