© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60335
    Prev
    Next
    INDEX
    Explanations

    security

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

    The neuron activates whenever the token “security” (in any casing or as part of a dotted identifier) appears.

    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
     Its
    -2.58
    .”
    -2.36
     Which
    -2.08
     です
    -2.02
     conceived
    -1.98
     nicknamed
    -1.96
     Anhänger
    -1.95
     presidencia
    -1.91
    一起来
    -1.89
     devoid
    -1.88
    POSITIVE LOGITS
    U
    2.66
    3
    2.25
    Ꭳ
    2.20
    B
    2.14
    6
    2.13
     \
    2.09
     conç
    2.06
    趼
    2.06
    ſty
    2.05
    r
    1.95
    Activations Density 0.008%

    No Known Activations