© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31458
    Prev
    Next
    INDEX
    Explanations

    у меня, у людей, у вас

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    2.06
    Բ
    1.89
    ᄈ
    1.83
     encomendas
    1.82
    ০
    1.80
    یم
    1.79
    exercises
    1.77
    oce
    1.77
     eğitimi
    1.74
    黜
    1.74
    POSITIVE LOGITS
    нің
    2.33
    ный
    2.22
    и
    2.19
    ों
    2.09
    ко
    2.06
    ్‌
    2.05
    ной
    2.03
    ные
    2.00
    ні
    2.00
    ру
    1.90
    Activations Density 0.003%

    No Known Activations