© 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. 16612
    Prev
    Next
    INDEX
    Explanations

    pairing, with, and

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

    pairing with

    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
    হইতে
    0.44
    Unnamed
    0.44
    銥
    0.42
    uedata
    0.42
    其中包括
    0.41
     الدین
    0.41
    اللہ
    0.40
     ટકા
    0.40
     えっと
    0.40
     વિભાગ
    0.39
    POSITIVE LOGITS
    搭配
    0.77
     pairing
    0.75
     paired
    0.69
     किंवा
    0.65
     Pairing
    0.62
     eller
    0.60
    或
    0.60
     pairings
    0.59
    pairing
    0.58
     recommended
    0.58
    Activations Density 0.179%

    No Known Activations