© 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-262K
    7. 16887
    Prev
    Next
    INDEX
    Explanations

    Admin, healthcare, and connections

    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
     endem
    0.50
     İstifadə
    0.47
    स्तेमाल
    0.46
    ⚘
    0.46
     spawning
    0.44
     EXPER
    0.44
     흡
    0.44
    ustering
    0.43
    orithm
    0.43
    工艺
    0.43
    POSITIVE LOGITS
    the
    0.46
     taxed
    0.45
     police
    0.44
    डिया
    0.42
    Police
    0.42
    ફ
    0.42
    Fre
    0.40
     policía
    0.40
    يس
    0.40
    itr
    0.40
    Activations Density 0.001%

    No Known Activations