© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7546
    Prev
    Next
    INDEX
    Explanations

    lift followed by mechanical apparatus or concepts

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

    The neuron fires strongly on occurrences of the word “lift.”

    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
     tetapi
    -2.39
    葑
    -2.30
    ቭ
    -2.20
    jenigen
    -2.16
    浮现
    -2.13
    LETIN
    -2.11
    翾
    -2.09
    泔
    -2.09
    il
    -2.08
    馐
    -2.08
    POSITIVE LOGITS
     yearn
    2.47
     δύο
    2.41
    ╿
    2.23
    két
    2.20
    ಞ
    2.20
     wedded
    2.20
     sullen
    2.20
     jarring
    2.17
    ственные
    2.16
    ꦁ
    2.16
    Activations Density 0.004%

    No Known Activations