© 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. 8368
    Prev
    Next
    INDEX
    Explanations

    journalism and news media

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

    This neuron is highly activated by terms related to legal/government contexts (e.g. amendments, courts, government, rights).

    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
     گیاه
    -1.56
     our
    -1.54
     растение
    -1.46
     your
    -1.33
    ׇ
    -1.26
     especially
    -1.24
     блюдо
    -1.18
     Maybe
    -1.15
    :
    -1.14
    <eos>
    -1.13
    POSITIVE LOGITS
    ּוֹ
    1.45
    וּ
    1.33
    ᾿
    1.30
    ׂ
    1.30
    usive
    1.29
    輟
    1.29
    música
    1.28
     PLAINTIFF
    1.28
     bukit
    1.27
     GRADUATE
    1.24
    Activations Density 0.395%

    No Known Activations