© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6355
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

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

    not X but Y

    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
     natomiast
    0.40
    types
    0.38
     যাওয়ার
    0.37
    cannot
    0.37
     যাওয়ার
    0.37
    sthe
    0.36
    wak
    0.36
    T
    0.35
     wakeup
    0.35
    ↵
    0.34
    POSITIVE LOGITS
     sondern
    0.84
     बल्कि
    0.83
     but
    0.77
     nhưng
    0.72
    而是
    0.63
     αλλά
    0.63
     hanem
    0.62
     بلکہ
    0.61
     lakini
    0.58
     ولكن
    0.58
    Activations Density 0.083%

    No Known Activations