© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24731
    Prev
    Next
    INDEX
    Explanations

    noun clauses after "to"

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ஈடுபட்ட
    0.38
     했던
    0.38
    者は
    0.37
    কারীরা
    0.37
     ചെയ്യുന്ന
    0.36
     فشاں
    0.36
    了一眼
    0.36
     செய்யும்
    0.35
    々は
    0.35
    蚬
    0.35
    POSITIVE LOGITS
     να
    1.48
    ที่จะ
    1.16
     să
    1.07
     to
    1.05
    要
    0.96
     anzu
    0.86
     ausz
    0.83
    ToSend
    0.82
     toBe
    0.82
     要
    0.80
    Activations Density 0.021%

    No Known Activations