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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 90701
    Prev
    Next
    INDEX
    Explanations

    code file mode lines

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

    The neuron fires on tokens with unusual orthography—especially those with uppercase letters or punctuation sequences (e.g. names like “Kramer” or Emacs mode markers like “-*-”).

    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
    0
    -2.91
     Their
    -2.34
    This
    -2.19
     Anſ
    -2.16
     ongeveer
    -2.14
    ствии
    -2.14
    疑惑
    -2.14
     perasaan
    -2.13
    ”;
    -2.13
     We
    -2.13
    POSITIVE LOGITS
    ⬯
    2.81
    囹
    2.48
    前辈
    2.28
     pointless
    2.25
    ными
    2.22
     あります
    2.20
     вернулся
    2.20
    絆
    2.20
    老爷子
    2.17
     prominent
    2.16
    Activations Density 0.012%

    No Known Activations