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

    Neuronpedia

    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. 21219
    Prev
    Next
    INDEX
    Explanations

    breaking down or explaining processes

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

    expository scaffolding in Q&A-style text: section headings, transitions, and discourse markers that structure explanations and breakdowns.

    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
     Collegiate
    0.43
     plas
    0.41
     diaspora
    0.40
     scholarly
    0.39
     commemorative
    0.39
    >?,
    0.39
     genotype
    0.39
     Plas
    0.39
     반려
    0.39
     philanthropic
    0.38
    POSITIVE LOGITS
    प्ताह
    0.45
    amano
    0.44
    ztal
    0.43
    Rek
    0.42
    tores
    0.40
    Prote
    0.39
     ويك
    0.39
    ㄡ
    0.39
    மில்லை
    0.39
    糟糕
    0.38
    Activations Density 6.117%

    No Known Activations