© 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. 37212
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions like while

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

    meanwhile or meanwhile/contrastive conjunctions

    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
     '[
    0.42
     !!
    0.41
     four
    0.40
    0.39
    9
    0.38
     '#
    0.38
     strings
    0.38
     nine
    0.38
    4
    0.38
     !!!!
    0.36
    POSITIVE LOGITS
     hingegen
    1.59
     natomiast
    1.56
     meanwhile
    1.38
     dagegen
    1.38
     Meanwhile
    1.19
     zaś
    1.18
    Meanwhile
    1.17
     meantime
    1.17
    则是
    1.12
    則是
    1.09
    Activations Density 0.110%

    No Known Activations