© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105120
    Prev
    Next
    INDEX
    Explanations

    rivers and geographical places

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

    The neuron specifically detects occurrences of the word “river” (especially its plural form “rivers”).

    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
     другая
    -2.63
    0
    -2.56
    两年
    -2.45
    หรือ
    -2.31
     этом
    -2.23
     ใน
    -2.20
    蘗
    -2.14
    इटम
    -2.13
    銦
    -2.11
     formidable
    -2.09
    POSITIVE LOGITS
    s
    2.94
    </h3>
    2.64
    та
    2.53
     обраща
    2.22
    瞜
    2.14
     inclui
    2.14
    獁
    2.13
    the
    2.11
     нужны
    2.09
    rivers
    2.09
    Activations Density 0.006%

    No Known Activations