© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69928
    Prev
    Next
    INDEX
    Explanations

    local or locally

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

    This neuron responds to structured, technical or “metadata‐style” tokens—numbers, timestamps, command- or path-like strings, and other quantifiers or environment labels.

    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
     edifício
    -1.06
     condomínio
    -1.04
     setAddress
    -0.84
    ⋊
    -0.82
    外国人
    -0.81
     eixo
    -0.81
    pageX
    -0.81
    смотра
    -0.80
     imóvel
    -0.80
    úblico
    -0.79
    POSITIVE LOGITS
     local
    8.38
    local
    6.91
     locally
    6.06
     мест
    5.53
    Local
    5.50
    LOCAL
    5.31
     lokal
    5.13
     LOCAL
    5.06
     Local
    4.88
    本地
    4.84
    Activations Density 0.525%

    No Known Activations