© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43584
    Prev
    Next
    INDEX
    Explanations

    pots and potted plants

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

    The neuron fires on occurrences of “pot” (e.g. pot, pots, potted)—i.e. mentions of pots or potted containers.

    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
    hhhh
    -2.33
    j
    -2.27
    罨
    -2.25
    蓥
    -2.22
     ragaz
    -2.22
    7
    -2.20
    驁
    -2.17
    婠
    -2.13
    that
    -2.08
    on
    -2.00
    POSITIVE LOGITS
    </strong>
    2.55
     What
    2.19
     целью
    2.17
    untamiento
    2.05
     AND
    1.95
    rugada
    1.95
    玨
    1.95
    utschland
    1.90
    ꜆
    1.89
     otras
    1.88
    Activations Density 0.004%

    No Known Activations