© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27829
    Prev
    Next
    INDEX
    Explanations

    names followed by specific punctuation

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

    This neuron detects the literal “EOF” marker used in code (often to denote the end of a file or here-document).

    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
      (
    -1.11
    cations
    -1.09
     makna
    -1.07
     alkoh
    -1.06
    lamps
    -1.05
    чики
    -1.04
    Ṅ
    -1.04
    taban
    -1.04
    asted
    -1.03
     ▸
    -1.01
    POSITIVE LOGITS
    あー
    0.97
    ];
    0.96
    entieth
    0.95
    時々
    0.93
    ごちそう
    0.91
    ときに
    0.91
    のお客様
    0.91
    昼食
    0.91
    様な
    0.91
    男の子
    0.90
    Activations Density 0.000%

    No Known Activations