© 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. 114216
    Prev
    Next
    INDEX
    Explanations

    similarity or likeness

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

    The neuron fires on tokens that are part of words expressing “similar” (e.g. similar, resembling, ähnlich, подоб) across different languages and contexts.

    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
    ));
    -2.55
    ):
    -2.44
    );
    -2.44
    ستارهای
    -2.41
    聍
    -2.23
     untuk
    -2.20
    裢
    -2.17
     subió
    -2.08
    ()]
    -2.06
    ㉕
    -2.06
    POSITIVE LOGITS
     the
    2.94
    儅
    2.75
     was
    2.19
    専用の
    2.05
     geringen
    1.96
    羕
    1.84
    形で
    1.84
     that
    1.81
    之类的
    1.80
    釹
    1.79
    Activations Density 0.011%

    No Known Activations