© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11483
    Prev
    Next
    INDEX
    Explanations

    Zanzibar

    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_65k_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
    illy
    0.55
    ill
    0.50
    äre
    0.47
    art
    0.46
    aco
    0.46
    itet
    0.46
    ore
    0.46
    ⁂
    0.45
    ente
    0.45
    pano
    0.45
    POSITIVE LOGITS
    詩
    0.49
     اسلامی
    0.49
     elves
    0.47
    mylist
    0.46
    suggestions
    0.45
    সেল
    0.45
     Shayari
    0.44
    джа
    0.43
     reconstit
    0.43
    اکي
    0.43
    Activations Density 0.013%

    No Known Activations