© 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. 32774
    Prev
    Next
    INDEX
    Explanations

    model turn

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

    The neuron strongly activates for the internal token "model" (the assistant/metadata token indicating the language model).

    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
     variáveis
    0.39
    ိတ်
    0.38
     heroism
    0.36
     ਸੁ
    0.36
     அனும
    0.36
    }($
    0.36
    崞
    0.36
    தீ
    0.35
     IMPRO
    0.35
    ikoa
    0.35
    POSITIVE LOGITS
    <0xC2>
    0.44
     listView
    0.44
     authoritative
    0.43
     ಅಧಿಕ
    0.42
    ppu
    0.41
    밥
    0.40
    ---
    0.39
     Increased
    0.39
     edu
    0.38
     যথাযথ
    0.38
    Activations Density 0.012%

    No Known Activations