© 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. 22-GEMMASCOPE-RES-131K
    4. 54365
    Prev
    Next
    INDEX
    Explanations

    html input type attribute

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

    This neuron detects the “type=” attribute on HTML input elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ℡
    -1.13
     any
    -1.12
    -};
    -1.09
    
    -1.08
    خیص
    -1.05
     münchen
    -1.05
     "..\..\..\
    -1.04
    ]:
    
    -1.04
    *************/
    -1.04
    britanni
    -1.03
    POSITIVE LOGITS
     unholy
    1.27
    ฌ
    1.07
     fath
    1.03
     bastion
    1.01
     condol
    1.00
     instead
    0.98
     abomination
    0.97
     aforementioned
    0.95
    Ashlee
    0.95
     zulassen
    0.94
    Activations Density 0.002%

    No Known Activations