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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4261
    Prev
    Next
    INDEX
    Explanations

    python code import

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

    code-block formatted programming snippets, especially with structured docstrings or comment sections (e.g., Args/Returns) in languages like Python/C/C++

    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_31_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
     kanamycin
    0.25
     पाण्यात
    0.25
     calomel
    0.24
     taker
    0.23
     বলিয়াই
    0.23
     oligonucleotide
    0.23
     ferrugineux
    0.23
     ligand
    0.23
     brine
    0.23
     OXIDES
    0.23
    POSITIVE LOGITS
    import
    0.41
    class
    0.36
    #
    0.36
    package
    0.34
    /
    0.33
    //
    0.30
    function
    0.30
    github
    0.29
    #!/
    0.28
    namespace
    0.28
    Activations Density 0.535%

    No Known Activations