© 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. 31-GEMMASCOPE-2-RES-262K
    7. 25361
    Prev
    Next
    INDEX
    Explanations

    large language model, trained by

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

    tokens that indicate the speaker’s identity as a large language model (words like "large", "language", "model" and related self‑identifying phrases/questions).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    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
    locks
    0.47
     resembled
    0.47
     resulted
    0.43
    becomes
    0.43
       
    0.43
    τού
    0.41
    ទ្រ
    0.41
         
    0.41
                         
    0.41
     becomes
    0.40
    POSITIVE LOGITS
     работаю
    0.67
    uyorum
    0.64
     знаю
    0.57
     हूं
    0.57
     jestem
    0.55
    ıyorum
    0.54
     atualmente
    0.54
    这意味着
    0.54
    我现在
    0.53
     আছি
    0.51
    Activations Density 0.133%

    No Known Activations