© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83666
    Prev
    Next
    INDEX
    Explanations

    related topic

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

    The neuron activates on occurrences of the word “related,” including hyphenated or compound uses of “related.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ).
    -1.89
    }$
    -1.88
    A
    -1.60
    ults
    -1.55
     favor
    -1.55
     your
    -1.55
     You
    -1.52
     us
    -1.48
     for
    -1.48
    "=>
    -1.45
    POSITIVE LOGITS
    を試
    2.13
     этом
    1.87
    夲
    1.86
    囖
    1.84
     couvrir
    1.77
     macetas
    1.77
     aufnehmen
    1.73
    ຝ
    1.72
     میکنم
    1.71
     talál
    1.70
    Activations Density 0.033%

    No Known Activations