© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1138
    Prev
    Next
    INDEX
    Explanations

    next, continuation, consecutive

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

    directive and meta-instructional scaffolding in chat-style prompts, especially role/format tags, command markup, and structured response templates indicating how to answer.

    oai_token-act-pair · gpt-5Triggered by @irajjmoradi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     sache
    0.85
     används
    0.80
     SMD
    0.79
    κρι
    0.77
     métall
    0.75
     overstated
    0.74
     zowel
    0.73
     HD
    0.73
     ochron
    0.72
     bescherm
    0.72
    POSITIVE LOGITS
     next
    1.26
    next
    1.20
     consecutive
    1.13
     consecutively
    1.09
     continuation
    1.07
     continuing
    1.06
    Next
    1.06
     नेक्स्ट
    1.02
     successively
    1.01
     successive
    1.01
    Activations Density 2.694%

    No Known Activations