© 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. 34-GEMMASCOPE-RES-131K
    7. 59180
    Prev
    Next
    INDEX
    Explanations

    secret / secrets

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

    This neuron is strongly triggered by API‐credential terms—tokens like “consumer,” “key,” “secret,” “token,” “client_id,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Vv
    -0.80
     Sensors
    -0.78
    Ck
    -0.77
    REMOTE
    -0.73
     спор
    -0.73
     mengen
    -0.73
    んび
    -0.73
     senador
    -0.73
     Nebula
    -0.71
    leen
    -0.71
    POSITIVE LOGITS
     secrets
    5.84
     secret
    5.44
    secret
    4.41
    secrets
    4.13
     Secrets
    3.88
     секре
    3.67
    Secrets
    3.64
    Secret
    3.58
     Secret
    3.52
    秘密
    3.47
    Activations Density 0.054%

    No Known Activations