© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93489
    Prev
    Next
    INDEX
    Explanations

    items following "include"

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

    The neuron detects list‐style or bullet‐point content—i.e. short instructional or enumerated items.

    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
    -2.28
     then
    -1.78
     of
    -1.70
    this
    -1.62
     This
    -1.59
    ykjav
    -1.53
     didn
    -1.41
    oded
    -1.36
     &#
    -1.29
    Legături
    -1.29
    POSITIVE LOGITS
    :
    4.84
    :
    
    2.55
    :……
    2.47
    ៖
    2.31
    :
    2.14
     şun
    2.13
    ():
    2.11
    ઃ
    1.96
     seguenti
    1.91
     følgende
    1.87
    Activations Density 0.674%

    No Known Activations