© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15689
    Prev
    Next
    INDEX
    Explanations

    key + following noun

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

    The neuron activates on any token containing “key” (e.g. key, Key, keying, keygen).

    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
     apnea
    0.59
    ○○
    0.57
    su
    0.56
    athione
    0.55
     breathed
    0.55
     plumb
    0.54
     hydrodynamic
    0.54
    ้อ
    0.53
     seguridad
    0.53
     breathing
    0.53
    POSITIVE LOGITS
    KEY
    1.05
    🔑
    1.01
     Key
    0.97
     KEY
    0.96
    hole
    0.94
     Keys
    0.93
     getKey
    0.91
     keys
    0.88
     key
    0.84
    Keys
    0.84
    Activations Density 0.074%

    No Known Activations