© 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. 10551
    Prev
    Next
    INDEX
    Explanations

    coding patterns and instructions

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

    the end-of-turn/conversation boundary marker (tokens like <end_of_turn>).

    oai_token-act-pair · gpt-5-miniTriggered 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
     Mathieu
    0.37
    Anth
    0.36
     Inde
    0.35
     Allied
    0.35
     affaires
    0.35
    WMat
    0.35
    🚶
    0.34
    gameOver
    0.34
    眇
    0.34
     Anth
    0.34
    POSITIVE LOGITS
    igator
    0.41
    ikal
    0.41
    izzata
    0.41
    ir
    0.38
    or
    0.38
     Hernandez
    0.37
     প্রাণের
    0.37
     documentation
    0.37
    lada
    0.37
     niece
    0.36
    Activations Density 0.050%

    No Known Activations