© 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. 119526
    Prev
    Next
    INDEX
    Explanations

    almonds, amygdala, Mandelbrot, Almond

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

    words related to almonds, almond products, or parts of the almond tree.

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

    The neuron detects mentions of almonds (and their botanical terms like Prunus and amygdalus).

    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
    erintah
    -2.28
     werd
    -2.23
    讠
    -2.13
    也要
    -2.03
     ナイロン
    -2.02
    ’，
    -2.02
    
    -2.02
    </sub>
    -2.00
     giù
    -2.00
     コットン
    -1.97
    POSITIVE LOGITS
    橚
    2.44
    
    2.38
    there
    2.25
    We
    2.17
    \
    2.16
    外界
    2.13
    ،
    2.09
    .,
    2.09
    It
    2.06
    Still
    2.00
    Activations Density 0.009%

    No Known Activations