© 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. 21748
    Prev
    Next
    INDEX
    Explanations

    but

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

    contrasting 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
    !!!!!
    0.54
    !!!!
    0.53
    !!!
    0.48
     tienen
    0.47
     diferentes
    0.46
    !!!!!!
    0.43
     त्यांच्या
    0.43
    i
    0.43
    cribing
    0.42
     YOU
    0.41
    POSITIVE LOGITS
     แต่
    0.94
    但我
    0.89
     lakini
    0.82
     लेकिन
    0.80
     لكن
    0.80
     אבל
    0.80
    但这
    0.79
     אך
    0.79
     nhưng
    0.78
     ولكن
    0.77
    Activations Density 0.000%

    No Known Activations