Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 15467
    Prev
    Next
    INDEX
    Explanations

    general context markers

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

    assistant-style, formatted explanatory output (structural/formatting markers and filler tokens) indicative of the model’s response rather than the user’s input.

    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
     Changing
    0.42
     abstraction
    0.42
    誅
    0.42
     multitudes
    0.42
     बदलने
    0.38
     ट्रायल
    0.38
     sebaik
    0.37
    砌
    0.37
     contenir
    0.36
     Aph
    0.36
    POSITIVE LOGITS
    _="
    0.46
    า
    0.44
    gü
    0.44
    sulf
    0.42
    ELD
    0.41
    })=\
    0.40
    Ale
    0.40
    ='/'
    0.40
    ALE
    0.40
     geçer
    0.39
    Activations Density 0.038%

    No Known Activations