© 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. 72068
    Prev
    Next
    INDEX
    Explanations

    full name or descriptor

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

    The neuron fires on occurrences of the word “full” (e.g. in identifiers like full_name, full_path, full_class_name, etc.).

    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
     เพราะ
    -2.52
    </u>
    -2.47
    CHREIB
    -2.38
    Leírás
    -2.34
     Of
    -2.30
    </h3>
    -2.27
     .
    -2.23
    ).
    -2.22
     pensar
    -2.11
     The
    -2.09
    POSITIVE LOGITS
    er
    5.44
    ه
    3.89
    ে
    2.83
    e
    2.77
    ு
    2.75
    erl
    2.55
    های
    2.52
    
    2.45
    ثمان
    2.45
    an
    2.44
    Activations Density 0.007%

    No Known Activations