© 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. 34098
    Prev
    Next
    INDEX
    Explanations

    code include directives

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

    The neuron fires on long runs of consecutive punctuation marks—most notably ellipses (sequences of multiple periods).

    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
     inconvénients
    -1.08
     diámetro
    -0.93
     jugu
    -0.92
    рак
    -0.90
     تصميم
    -0.90
     koncentr
    -0.90
    utama
    -0.90
     maría
    -0.89
     flecha
    -0.89
    Jalan
    -0.88
    POSITIVE LOGITS
    すぎ
    0.98
     AssemblyCulture
    0.95
     beginnetje
    0.94
    磋
    0.94
    })));
    0.93
    ษ
    0.91
    不但
    0.90
    ')));
    0.86
    єра
    0.85
     you
    0.85
    Activations Density 0.000%

    No Known Activations