© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64208
    Prev
    Next
    INDEX
    Explanations

    location or containment

    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
    a
    0.55
     сложно
    0.51
    话
    0.50
    怦
    0.50
    ພວກເຮ
    0.46
     работа
    0.46
     рекоменда
    0.45
     फै
    0.45
     času
    0.44
     soạn
    0.44
    POSITIVE LOGITS
    ет
    0.53
     ”,
    0.52
    ер
    0.48
    isub
    0.48
    い
    0.47
    می
    0.46
    mapsto
    0.45
    isio
    0.45
    いだ
    0.45
    еры
    0.45
    Activations Density 0.008%

    No Known Activations