© 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. 84827
    Prev
    Next
    INDEX
    Explanations

    indent and justification

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

    The neuron activates primarily on numeric tokens (digits, numbers, measurements, and related punctuation).

    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
     puzzle
    -0.76
     هذا
    -0.74
    timi
    -0.74
    猗
    -0.71
    onya
    -0.70
     rec
    -0.69
    ONIC
    -0.69
    værk
    -0.68
     Krakowie
    -0.68
     kim
    -0.68
    POSITIVE LOGITS
     indent
    1.02
    indent
    1.00
     indented
    0.90
     problems
    0.86
    。『
    0.84
     justify
    0.82
    justify
    0.81
    🛰
    0.81
     indentation
    0.80
    Indent
    0.80
    Activations Density 0.021%

    No Known Activations