© 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. 22-GEMMASCOPE-RES-131K
    4. 67372
    Prev
    Next
    INDEX
    Explanations

    westerly winds and ocean currents

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

    scientific or technical content related to meteorology, oceanography, and atmospheric phenomena.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on domain-specific scientific and geographic terms—especially proper nouns (e.g. place names), technical nouns, and numeric or measurement expressions.

    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
     your
    -1.96
     金属
    -1.61
     trabajador
    -1.59
    SALUD
    -1.54
    轳
    -1.52
    ﺅ
    -1.49
     diskusi
    -1.48
    Hva
    -1.45
     originali
    -1.44
    Ahol
    -1.43
    POSITIVE LOGITS
     and
    1.55
     February
    1.48
    ,
    1.46
     April
    1.45
     at
    1.42
     September
    1.41
     January
    1.38
     in
    1.36
     wektor
    1.36
    兵衛
    1.35
    Activations Density 0.040%

    No Known Activations