© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129298
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on the “shebang” sequence (#!/) that begins a script file.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    script interpreter directives

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ?』
    -2.22
     to
    -1.93
    そして
    -1.91
    …?
    -1.83
    などを
    -1.82
    つまり
    -1.81
    けどね
    -1.80
    でも
    -1.78
     by
    -1.78
    日記
    -1.77
    POSITIVE LOGITS
    為に
    2.14
    つづく
    2.08
    あー
    2.06
     decidedly
    2.00
    おそ
    1.99
    ほら
    1.98
    ようになります
    1.91
    ふと
    1.91
     sembler
    1.86
    久し
    1.81
    Activations Density 0.003%

    No Known Activations