© 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. 7637
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    The neuron is effectively dead—it never responds to any tokens and thus doesn’t detect any pattern.

    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
    ח
    1.00
    лин
    0.88
    स
    0.87
    на
    0.82
    r
    0.82
    ཿ
    0.80
     compared
    0.76
    اس
    0.75
    ଦ
    0.75
    न
    0.73
    POSITIVE LOGITS
     autre
    0.96
     altro
    0.95
     zcela
    0.81
     bekas
    0.80
     notte
    0.79
     doré
    0.77
     spécifique
    0.76
     métallique
    0.75
     douloureuse
    0.75
     propriété
    0.75
    Activations Density 0.001%

    No Known Activations