© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 38670
    Prev
    Next
    INDEX
    Explanations

    recursive and dfs methods

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

    The neuron fires on mentions of recursion or graph/tree‐traversal algorithms (e.g. words like “recursive,” “depth-first,” “flood-fill,” “bfs,” “dfs,” “scan,” etc.).

    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
    vermectin
    -1.63
    addTo
    -1.39
    rfan
    -1.31
     Berech
    -1.27
    饪
    -1.23
     necesit
    -1.23
     هناك
    -1.21
    `;
    -1.21
     Differenz
    -1.21
    ↵↵
    -1.20
    POSITIVE LOGITS
     from
    1.81
     the
    1.77
     our
    1.51
     each
    1.45
    ingtones
    1.43
     باتری
    1.41
     into
    1.38
    the
    1.38
     out
    1.33
     as
    1.31
    Activations Density 0.031%

    No Known Activations