© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6988
    Prev
    Next
    INDEX
    Explanations

    public keys anonymous

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

    The neuron flags tokens and phrases that look like credentials or secret configuration parameters—e.g. keys, secrets, access tokens, IDs, and similar authentication data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     감소
    0.61
    OrderFlight
    0.59
    व्यों
    0.59
    steelblue
    0.58
    ്യത
    0.57
     চিং
    0.57
    🎌
    0.57
     वेजिट
    0.56
     rammed
    0.56
    鿓
    0.56
    POSITIVE LOGITS
    apiKey
    1.63
     apiKey
    1.45
    ApiKey
    1.45
    apikey
    1.41
     secret
    1.27
    secret
    1.25
    Secret
    1.22
     token
    1.21
    密钥
    1.21
    SECRET
    1.19
    Activations Density 0.072%

    No Known Activations