© 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. 22-GEMMASCOPE-RES-131K
    7. 34544
    Prev
    Next
    INDEX
    Explanations

    identifiers and assignments

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

    The neuron is tuned to spots in code where an object’s property is accessed via dot notation and then assigned a value (i.e. `object.property = …`).

    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
     then
    -0.94
     Bewohner
    -0.93
     initially
    -0.83
    Roasted
    -0.82
     upang
    -0.79
     Gläub
    -0.77
    龛
    -0.77
    restes
    -0.77
     সে
    -0.76
     preload
    -0.74
    POSITIVE LOGITS
     désigner
    0.89
    zens
    0.88
     anything
    0.87
    上下文
    0.84
     access
    0.84
    NameExpr
    0.82
     بلا
    0.82
    🤯
    0.81
     دسترسی
    0.81
     refers
    0.81
    Activations Density 0.076%

    No Known Activations