© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15415
    Prev
    Next
    INDEX
    Explanations

    css-cascade tag

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

    The neuron is picking up on code‐ or markup‐style tokens and punctuation sequences (e.g. file names, tags, ellipses, triple dots, punctuation marks, and other technical/tokenized elements).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    シック
    -0.90
    jemahan
    -0.87
     Terminology
    -0.84
     dégust
    -0.84
     SqlParameter
    -0.84
     соответству
    -0.82
    ypso
    -0.82
     kokos
    -0.81
     estén
    -0.81
    compare
    -0.81
    POSITIVE LOGITS
    ální
    0.95
    ėms
    0.94
    requipa
    0.91
    ("}");
    0.83
    Mek
    0.83
    prender
    0.82
    lesia
    0.82
    廊下
    0.81
     erheben
    0.81
     Makes
    0.81
    Activations Density 0.073%

    No Known Activations