© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4336
    Prev
    Next
    INDEX
    Explanations

    platform, potential, triggered

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

    The neuron flags the single most content‐bearing (i.e. semantically salient or “key”) word in each snippet.

    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_24_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
    ও
    0.97
    s
    0.92
    pas
    0.86
    ের
    0.84
    ים
    0.83
    ς
    0.79
    resource
    0.79
    ionario
    0.79
     ресурс
    0.76
     también
    0.75
    POSITIVE LOGITS
     imputed
    0.80
     encircled
    0.76
    р
    0.75
    ू
    0.74
     rejo
    0.73
    šću
    0.72
    ำ
    0.70
     hashMap
    0.70
    ̾
    0.70
     rooted
    0.70
    Activations Density 0.001%

    No Known Activations