© 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. 22-GEMMASCOPE-RES-131K
    7. 104238
    Prev
    Next
    INDEX
    Explanations

    Order before 3pm

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

    This neuron fires on the numbers that mark the start of added lines in unified-diff hunk headers (e.g. the “+3,162” or “+109.5” offsets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    erialize
    -1.16
    Aantal
    -1.15
     balón
    -1.13
    佺
    -1.12
     siè
    -1.10
    WidgetItem
    -1.09
    Thêm
    -1.09
     capuz
    -1.09
    niei
    -1.09
    árbol
    -1.09
    POSITIVE LOGITS
    P
    1.20
    R
    1.14
    D
    1.09
    pa
    1.06
    Sa
    1.05
    L
    1.05
    !
    1.04
    N
    1.01
    O
    1.00
     j
    1.00
    Activations Density 0.000%

    No Known Activations