© 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. 42695
    Prev
    Next
    INDEX
    Explanations

    shell scripting bash `declare` `read` `setopt`

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

    The neuron is triggered by Bash arithmetic for‐loop syntax, i.e. the “for ((…;…;…)); do” construct.

    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
     rehabilitación
    -1.27
    eens
    -1.19
     hormigón
    -1.19
     kteří
    -1.10
     bambú
    -1.08
     ((*
    -1.08
     solchen
    -1.05
     actualización
    -1.05
     solche
    -1.05
    ของ
    -1.05
    POSITIVE LOGITS
    prised
    1.16
    tened
    1.09
     umid
    1.08
    [
    1.08
     جمعه
    1.08
     when
    1.05
     holde
    0.99
    use
    0.99
     dad
    0.98
     do
    0.98
    Activations Density 0.304%

    No Known Activations