© 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. 23563
    Prev
    Next
    INDEX
    Explanations

    want or 5

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

    This neuron fires most strongly on long runs of space characters (i.e. indentation).

    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
    ‌ی
    -0.85
                        
    -0.85
     seven
    -0.79
    七
    -0.76
     '../../../
    -0.76
                            
    -0.75
                
    -0.75
    ../../../
    -0.73
    ueras
    -0.72
    CBS
    -0.71
    POSITIVE LOGITS
    1.63
     want
    1.45
     fifth
    1.05
    Want
    1.05
     wanting
    1.04
    want
    1.01
     wants
    0.99
    5
    0.98
    0.96
     ingin
    0.94
    Activations Density 0.025%

    No Known Activations