© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71796
    Prev
    Next
    INDEX
    Explanations

    npm commands

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

    The neuron activates on occurrences of the “npm” token (and closely associated npm commands like install, run, start, update) in package‐management contexts.

    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
     said
    -2.61
    潆
    -2.53
    งิน
    -2.53
    鲀
    -2.50
     plusieurs
    -2.50
    的问道
    -2.47
    
    -2.45
    尛
    -2.41
    霂
    -2.38
     {
    -2.34
    POSITIVE LOGITS
    t
    3.31
    When
    2.78
    During
    2.63
    Because
    2.41
     テ
    2.36
    ?
    2.36
    Having
    2.34
    ㉕
    2.33
    ри
    2.33
    If
    2.31
    Activations Density 0.004%

    No Known Activations