© 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. 6519
    Prev
    Next
    INDEX
    Explanations

    but or nor conjunctions

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

    distinguishing between options

    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
     असल्या
    0.36
     আৰু
    0.35
     உட்பட
    0.34
     Và
    0.33
    "/>
    0.33
     হওয়ায়
    0.32
     Aufgrund
    0.32
     સહિત
    0.32
    और
    0.32
    utches
    0.32
    POSITIVE LOGITS
    而是
    1.18
     बल्कि
    1.04
     بلکه
    0.99
     sondern
    0.98
     hanem
    0.88
     بلکہ
    0.82
     sino
    0.78
     nor
    0.74
    nor
    0.61
    ;
    0.61
    Activations Density 0.341%

    No Known Activations