© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2745
    Prev
    Next
    INDEX
    Explanations

    bulleted list items

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

    The neuron fires on list-item markers and formatting tokens (e.g. bullets, dashes, bracketed indices) that denote entries in a list.

    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
     and
    -2.25
     also
    -1.91
     other
    -1.64
     this
    -1.59
     that
    -1.55
     these
    -1.54
    Also
    -1.50
     también
    -1.48
     також
    -1.46
    Также
    -1.43
    POSITIVE LOGITS
    <strong>
    2.09
    <b>
    1.80
    1.78
         
    1.67
     The
    1.66
     Firstly
    1.66
             
    1.61
    当然是
    1.59
           
    1.59
        
    1.59
    Activations Density 0.055%

    No Known Activations