© 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. 69131
    Prev
    Next
    INDEX
    Explanations

    alt-tab, alt+f2, altman, altschool

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

    The neuron specifically fires for mentions of the “Alt” key (especially in “Alt-tab” or other Alt-shortcut sequences).

    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
    鋮
    -1.99
    sandalia
    -1.92
    阉
    -1.91
     sogen
    -1.89
    嘁
    -1.85
    勦
    -1.84
    ﹂
    -1.84
    ㆆ
    -1.83
    ⴱ
    -1.82
     produse
    -1.80
    POSITIVE LOGITS
    ----
    2.20
    。
    2.08
    .............
    2.03
     '
    2.02
     disbursed
    2.00
    [
    2.00
    𖣘
    2.00
    liebte
    1.99
    就
    1.98
     craz
    1.97
    Activations Density 0.007%

    No Known Activations