© 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. 22-GEMMASCOPE-RES-131K
    7. 72741
    Prev
    Next
    INDEX
    Explanations

    units of measurement

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

    The main thing this neuron does is find metric distance units (e.g., m, km, cm) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    おわりに
    -1.20
    来週
    -1.16
     também
    -1.13
     trám
    -1.12
    総評
    -1.12
    のバ
    -1.11
    veret
    -1.09
    何でも
    -1.09
    っている
    -1.09
    ようで
    -1.05
    POSITIVE LOGITS
    <bos>
    1.09
    Ingredi
    1.05
    எ
    0.98
    tidumbre
    0.96
    )
    0.94
    ingale
    0.89
    anzeigen
    0.88
    誼
    0.88
    خد
    0.88
    資料來源
    0.87
    Activations Density 0.003%

    No Known Activations