© 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. 24-GEMMASCOPE-2-RES-262K
    7. 1805
    Prev
    Next
    INDEX
    Explanations

    knowledge to survive stories

    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_24_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
    ların
    0.42
    의
    0.41
     içerisinde
    0.38
    들의
    0.38
    のリ
    0.38
    anın
    0.37
     olan
    0.36
     arasında
    0.36
    ları
    0.36
    ınız
    0.35
    POSITIVE LOGITS
     тщательно
    0.43
    𝚔
    0.42
     चांगली
    0.41
     технику
    0.40
    Mechan
    0.40
     тща
    0.40
     чемпионаты
    0.40
     некоторое
    0.39
     когда
    0.39
     тяжело
    0.39
    Activations Density 0.000%

    No Known Activations