© 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. 10-GEMMASCOPE-RES-131K
    4. 41919
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

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

    The neuron is detecting diff hunk header lines (those beginning with “@@”) in patch/​diff text.

    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
     T
    -1.53
     C
    -1.35
    ↵
    -1.30
     Amazing
    -1.26
     !
    -1.26
     bajo
    -1.24
     (
    -1.22
    })_{
    -1.20
     children
    -1.20
     Y
    -1.19
    POSITIVE LOGITS
     praktische
    1.48
     certamente
    1.45
     were
    1.44
     COMFORT
    1.40
     rehabilitación
    1.39
     zubehör
    1.38
    selben
    1.35
     グリル
    1.35
    腚
    1.34
     CREAT
    1.33
    Activations Density 0.004%

    No Known Activations