© 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. 22812
    Prev
    Next
    INDEX
    Explanations

    bar elements

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

    This neuron detects the occurrence of the substring “bar” (including in hyphenated or suffixed forms) in tokens.

    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
    饪
    -2.34
    芎
    -2.03
    ъ
    -1.91
    蟜
    -1.90
    rolment
    -1.88
    潆
    -1.88
    ៚
    -1.88
    𝘍
    -1.79
    푣
    -1.79
    </h5>
    -1.75
    POSITIVE LOGITS
    )--
    2.44
    }$
    2.44
    </strong>
    2.39
    .)
    2.27
    ";
    2.22
    )$
    2.19
    );
    2.09
    )-
    2.06
    .;
    2.02
    --
    2.02
    Activations Density 0.032%

    No Known Activations