Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 176
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     akkor
    0.58
    ۰۰
    0.52
     comenzar
    0.48
     brasile
    0.47
     sayı
    0.45
     estrellas
    0.44
     Kelas
    0.44
    𝖽
    0.44
     pertanyaan
    0.44
     diámetro
    0.44
    POSITIVE LOGITS
    ங்கிணை
    0.55
    心思
    0.54
    ía
    0.47
    િ
    0.47
    ਾ
    0.45
    性と
    0.44
    ্ড
    0.43
    。
    0.43
    ov
    0.42
    ленні
    0.42
    Activations Density 3.702%

    No Known Activations