© 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. 10-GEMMASCOPE-RES-131K
    7. 39397
    Prev
    Next
    INDEX
    Explanations

    security permissions and validation exceptions

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

    The neuron is triggered by code tokens referring to security permission declarations (e.g. “Permissions,” “Permission,” and related security API keywords).

    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
     at
    -1.56
     \
    -1.16
    лся
    -1.15
     did
    -1.12
     who
    -1.12
    售价
    -1.11
     stylish
    -1.10
    ing
    -1.09
    jsoup
    -1.09
    in
    -1.08
    POSITIVE LOGITS
     både
    1.42
     作業
    1.41
     案例
    1.37
     tandis
    1.36
    <bos>
    1.32
     necesarias
    1.31
     чого
    1.30
     事例
    1.27
     directamente
    1.27
     场景
    1.27
    Activations Density 0.057%

    No Known Activations