© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42788
    Prev
    Next
    INDEX
    Explanations

    weight in pounds

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

    The neuron recognizes mentions of weights expressed in pounds.

    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
     mesmer
    -2.30
    satunya
    -2.28
     behöver
    -2.22
    喾
    -2.16
    CHREIB
    -2.09
    嬲
    -2.09
    ynek
    -2.06
    颙
    -2.06
     unrelenting
    -2.06
    非常的
    -2.05
    POSITIVE LOGITS
    ↵↵
    3.36
    <
    2.48
    <bos>
    2.47
     pounds
    2.34
    вом
    2.34
    -
    2.33
    ),
    2.33
     должна
    2.28
    <td>
    2.25
    у
    2.11
    Activations Density 0.001%

    No Known Activations