© 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. 68669
    Prev
    Next
    INDEX
    Explanations

    https:// or Project

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

    This neuron detects references to JSON resource specification files in AWS CloudFront URLs (e.g. CloudFormation ResourceSpecification.json links).

    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
    jectures
    -1.19
    ׇ
    -1.16
    ::$_
    -1.04
    ℤ
    -1.02
    眺望
    -0.96
     Erzb
    -0.95
     slovens
    -0.95
     verbally
    -0.94
    蛧
    -0.93
     ставить
    -0.92
    POSITIVE LOGITS
    ּוֹ
    1.11
    zys
    1.09
     отлично
    1.05
     changements
    1.05
     ASSISTANT
    1.03
     soluzione
    1.02
     conséquences
    1.02
     possibilités
    1.02
     riguard
    1.01
     publicités
    1.00
    Activations Density 0.001%

    No Known Activations