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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42125
    Prev
    Next
    INDEX
    Explanations

    combination of or combined with

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    0.84
    Norm
    0.62
    د
    0.59
    client
    0.59
    Rad
    0.58
    year
    0.58
    4
    0.58
    ن
    0.58
    FL
    0.55
    Fallback
    0.55
    POSITIVE LOGITS
     combinación
    1.00
    組み合わせ
    0.89
     combinação
    0.87
     combin
    0.85
     комбина
    0.84
     combinar
    0.80
     combinado
    0.75
     Combin
    0.75
     combinations
    0.75
     kombin
    0.70
    Activations Density 0.027%

    No Known Activations