© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    varying length

    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
     ज्यात
    0.51
    accès
    0.48
    жмите
    0.46
    б
    0.46
     результа
    0.45
     использованием
    0.45
    ड
    0.44
    ләү
    0.44
     США
    0.44
     Дон
    0.44
    POSITIVE LOGITS
     protons
    0.47
     entire
    0.44
     whole
    0.40
     proximal
    0.39
     pectin
    0.39
     strlen
    0.39
     &&
    0.38
     cleft
    0.38
     nejen
    0.38
     boolean
    0.38
    Activations Density 0.094%

    No Known Activations