© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76776
    Prev
    Next
    INDEX
    Explanations

    adding items to lists

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

    This neuron fires on the object-member access operator “.” (i.e. the dot before a method or field access).

    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
     novin
    -0.84
    而又
    -0.81
     rağmen
    -0.75
    ulir
    -0.75
     počíta
    -0.74
    Push
    -0.74
     şart
    -0.73
    yayım
    -0.72
    gång
    -0.71
     肥
    -0.71
    POSITIVE LOGITS
     add
    2.20
    add
    1.96
     adds
    1.84
     adding
    1.82
     added
    1.76
    Add
    1.67
     Adds
    1.56
     Add
    1.55
    添加
    1.53
     اضافه
    1.53
    Activations Density 0.005%

    No Known Activations