© 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. 22-GEMMASCOPE-RES-131K
    7. 24931
    Prev
    Next
    INDEX
    Explanations

    public class members

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

    The neuron fires on code method signatures—particularly access modifiers (like public/protected) and return‐type or function‐declaration 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    aneity
    -1.03
     بسیار
    -1.02
    trabajo
    -0.96
     acoso
    -0.96
     Če
    -0.96
    hacia
    -0.96
    lity
    -0.94
    bodied
    -0.93
     at
    -0.91
    Nguy
    -0.90
    POSITIVE LOGITS
    因此
    0.94
    ことで
    0.94
     dziel
    0.92
    </b>
    0.90
    ここまで
    0.88
    constructor
    0.88
     utveckling
    0.88
    の作成
    0.86
     `;
    0.86
    undefined
    0.85
    Activations Density 0.005%

    No Known Activations