© 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. 8264
    Prev
    Next
    INDEX
    Explanations

    love and life in multiple languages

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

    The neuron fires on tokens that are part of song or track titles (proper names of songs/artists).

    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
     මෙම
    0.83
    헥
    0.81
     بشكل
    0.80
     prévue
    0.80
     provenant
    0.77
    ≻
    0.77
     практически
    0.77
    ற்கான
    0.76
    ستخدم
    0.76
     utilisateur
    0.76
    POSITIVE LOGITS
     gön
    0.83
     deewana
    0.79
    把你
    0.77
     وطن
    0.75
     Tuhan
    0.72
     قیامت
    0.72
     insan
    0.70
     사랑
    0.69
     ن
    0.68
     Immortal
    0.68
    Activations Density 0.150%

    No Known Activations