© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    professional background

    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
    ра
    1.29
    í
    1.09
    δήποτε
    1.02
    써
    1.02
    ق
    0.97
    šao
    0.95
    <0xA5>
    0.94
     υπάρχ
    0.89
    š
    0.89
     dzień
    0.88
    POSITIVE LOGITS
    تك
    1.09
    یان
    1.08
    tir
    1.02
    tia
    0.97
    𝒾
    0.97
    دن
    0.97
     Xan
    0.97
    𝐓
    0.96
    tion
    0.94
    𝘢
    0.94
    Activations Density 0.004%

    No Known Activations