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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22101
    Prev
    Next
    INDEX
    Explanations

    real-world concepts and examples

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that serve as salient section/annotation markers or content-heavy keywords in technical/expository text (e.g., headings, labels, and emphasized informative terms).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    煊
    0.42
     ఉన్నాయి
    0.39
    곍
    0.39
    Movies
    0.39
    争取
    0.39
    夫
    0.39
     شار
    0.38
    ȱ
    0.38
     президента
    0.38
     стре
    0.37
    POSITIVE LOGITS
     Production
    0.48
     Note
    0.46
     accolade
    0.45
     noteworthy
    0.43
     Lessor
    0.43
     malgré
    0.43
     Asian
    0.42
     gak
    0.42
     TestBed
    0.41
     nth
    0.41
    Activations Density 0.155%

    No Known Activations