© 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. 199972
    Prev
    Next
    INDEX
    Explanations

    HTML explanation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     History
    0.52
    history
    0.51
     นึง
    0.51
     Ministries
    0.49
    université
    0.49
     Oriente
    0.48
     Histoire
    0.47
    v
    0.47
     symmetries
    0.46
     निवार
    0.46
    POSITIVE LOGITS
    مه
    0.47
     المه
    0.43
     garg
    0.41
    等方面
    0.41
     față
    0.40
    heten
    0.40
     dés
    0.40
     hydrophilic
    0.39
     smelled
    0.39
    、
    0.39
    Activations Density 0.002%

    No Known Activations