© 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-262K
    7. 42125
    Prev
    Next
    INDEX
    Explanations

    combination and combine

    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
    0
    0.90
    Rad
    0.72
    د
    0.66
    P
    0.64
    4
    0.63
    TEM
    0.62
    L
    0.62
    Dec
    0.61
    C
    0.61
    FLOAT
    0.61
    POSITIVE LOGITS
     combinación
    0.99
    組み合わせ
    0.87
     combinação
    0.82
     Combin
    0.78
     комбина
    0.78
     combinar
    0.76
     combinations
    0.74
    와의
    0.73
    ine
    0.72
     combine
    0.71
    Activations Density 0.026%

    No Known Activations