© 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. 20603
    Prev
    Next
    INDEX
    Explanations

    crank, cran, ratchet

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

    The neuron is tuned to detect occurrences of the substring “crank” (as in crank, crank arm, crankshaft, cranked, etc.).

    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
     But
    -3.70
     Verständ
    -2.34
    훙
    -2.31
     Altogether
    -2.31
     razões
    -2.25
     becas
    -2.25
     decidedly
    -2.22
    蹓
    -2.22
    ING
    -2.22
     Therefore
    -2.20
    POSITIVE LOGITS
    ！！”
    2.36
    ！！！”
    2.27
    ～！
    2.25
     姆
    2.14
    🪟
    2.11
     脸
    2.08
    愎
    2.08
    ～～
    2.08
    کید
    2.05
    ～♪
    2.03
    Activations Density 0.003%

    No Known Activations