© 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. 101745
    Prev
    Next
    INDEX
    Explanations

    requirement and needing

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

    The main thing this neuron does is find words and morphemes related to “require” (e.g., require, required, requirement, requiring).

    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
    ."
    -2.67
    \
    -2.52
    )
    -2.44
    揩
    -2.17
    '
    -2.17
    A
    -2.16
    “
    -2.16
    ?”
    -1.98
     在
    -1.97
    ꜆
    -1.92
    POSITIVE LOGITS
    鰾
    2.73
    ญี่ป
    2.34
    勦
    2.13
    
    2.11
    勍
    2.06
     transparencia
    2.05
    駡
    2.05
     soldadura
    2.03
    ний
    2.03
     attesa
    2.00
    Activations Density 0.104%

    No Known Activations