© 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. 7587
    Prev
    Next
    INDEX
    Explanations

    remaining quantities

    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
    そもそも
    0.41
     چندین
    0.41
     mehrere
    0.41
     někol
    0.40
    หลาย
    0.39
     vorige
    0.39
     considérée
    0.39
    𒅗
    0.39
    ළ
    0.38
     eerste
    0.38
    POSITIVE LOGITS
     remaining
    1.54
     나머지
    1.50
     나머
    1.45
     остальные
    1.42
     বাকি
    1.39
    剩下的
    1.35
     остальных
    1.34
    Remaining
    1.33
     Remaining
    1.33
     restantes
    1.28
    Activations Density 0.165%

    No Known Activations