© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4531
    Prev
    Next
    INDEX
    Explanations

    ward or wardens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ال
    1.35
     a
    1.28
    на
    1.26
    1
    1.23
    3
    1.19
    5
    1.18
    ne
    1.16
    是
    1.16
    ה
    1.15
    ischen
    1.14
    POSITIVE LOGITS
    نی
    1.26
    1.25
     созда
    1.13
    <0x80>
    1.11
    Ward
    1.09
    ໃນ
    1.08
    行う
    1.07
     ward
    1.06
     написа
    1.05
    ایی
    1.04
    Activations Density 0.001%

    No Known Activations