© 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. 10-GEMMASCOPE-RES-131K
    4. 123531
    Prev
    Next
    INDEX
    Explanations

    location within or near bodies of water

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

    The neuron detects geographic and locational descriptors—words indicating place names, borders, directional positions, and related context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    原始内容存档于
    -2.11
     then
    -1.73
     using
    -1.65
     when
    -1.59
    celotti
    -1.55
    Dış
    -1.48
     nové
    -1.44
     பய
    -1.41
    hidrat
    -1.41
     by
    -1.41
    POSITIVE LOGITS
    ,
    1.49
    скур
    1.25
    rous
    1.17
     of
    1.17
    ୀ
    1.15
     большинстве
    1.13
     karde
    1.12
    攥
    1.10
     decorativo
    1.10
     again
    1.10
    Activations Density 0.420%

    No Known Activations