© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34869
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions and related phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ">
    0.37
     pouvoir
    0.33
     ...
    0.32
    indungan
    0.32
    agar
    0.32
     इनको
    0.31
     &
    0.31
    نی
    0.31
    Vis
    0.31
     सॉरी
    0.31
    POSITIVE LOGITS
     during
    1.42
     durante
    1.27
    during
    1.20
     tijdens
    1.16
     DURING
    1.14
     během
    1.11
     when
    1.09
     podczas
    1.07
     whenever
    1.05
     خلال
    1.05
    Activations Density 0.018%

    No Known Activations