© 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. 34-GEMMASCOPE-RES-131K
    7. 115977
    Prev
    Next
    INDEX
    Explanations

    command line prompt

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

    This neuron fires on procedural, imperative command-line instructions—e.g. “open a terminal,” “at the prompt enter,” step-by-step shell or recovery-mode commands.

    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
     gula
    -0.81
     Sneaker
    -0.73
     tän
    -0.73
    aluno
    -0.73
     panna
    -0.71
    订单
    -0.71
     adipose
    -0.71
     Monza
    -0.71
    ciana
    -0.70
    EDUCATION
    -0.68
    POSITIVE LOGITS
     prompt
    3.73
     Prompt
    3.09
    prompt
    3.09
    Prompt
    2.97
    PROMPT
    2.41
     prompts
    2.25
     PROM
    2.08
     promptly
    2.02
     promp
    1.98
     prompting
    1.70
    Activations Density 0.130%

    No Known Activations