© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32892
    Prev
    Next
    INDEX
    Explanations

    `.h` or `.c` file paths

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

    The neuron strongly fires on mentions of software and technical product names (e.g. Vim, Terminal, iTerm2, include headers) rather than ordinary words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    優先
    -0.75
     prioritise
    -0.75
    女主
    -0.75
    优先
    -0.74
     lepton
    -0.71
    Manuscript
    -0.68
     prioritizing
    -0.68
     embracing
    -0.68
    Classi
    -0.67
    界面
    -0.67
    POSITIVE LOGITS
     titul
    0.84
    =`
    0.83
    Split
    0.81
     Warne
    0.80
    ALOG
    0.78
     dissociation
    0.77
     splitting
    0.76
    멍
    0.76
    bard
    0.75
     Kors
    0.75
    Activations Density 0.032%

    No Known Activations