© 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. 48501
    Prev
    Next
    INDEX
    Explanations

    child, d, Projection, Dogs, j, Rec, t

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

    The neuron is triggered by code‐related structural keywords—especially terms used in object or tree/loop constructs (e.g. object, loop, node, child).

    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
     (
    -1.45
     in
    -1.32
     a
    -1.08
    paedia
    -1.05
     can
    -1.05
     though
    -1.05
     although
    -1.03
    Meskipun
    -1.03
    как
    -1.03
    here
    -1.02
    POSITIVE LOGITS
    følge
    1.25
    gning
    1.13
     this
    1.10
    選んだ
    1.09
    EDY
    1.06
     ͡
    1.06
    这类
    1.05
     ภาพ
    1.05
     تلك
    1.04
     Sloveniji
    1.04
    Activations Density 0.554%

    No Known Activations