© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128008
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on various forms of the root “cultivat-,” i.e. words about cultivation or growing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    cultivation and cultivating

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

    The neuron detects forms of the word "cultivate" or "cultivation" in scientific and agricultural contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    僦
    -2.58
    甃
    -2.42
    './
    -2.42
    甚麼
    -2.34
     piele
    -2.25
    梘
    -2.17
     continuare
    -2.13
    杁
    -2.11
    厲害
    -2.11
     weiße
    -2.11
    POSITIVE LOGITS
     “
    3.17
     exuberant
    2.53
     unwavering
    2.52
    o
    2.48
    ?”
    2.20
    at
    2.11
    )
    2.08
     детьми
    2.03
     groundbreaking
    2.02
     cheerful
    1.99
    Activations Density 0.016%

    No Known Activations