© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1304
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    but
    1.25
     but
    1.12
    。
    1.07
    But
    1.02
    .
    0.99
     But
    0.95
    BUT
    0.94
    ។
    0.92
    。『
    0.91
    。「
    0.90
    POSITIVE LOGITS
     unlike
    2.13
    unlike
    1.97
     unsurprisingly
    1.92
     contrairement
    1.80
     помимо
    1.77
     however
    1.76
     despite
    1.75
     conversely
    1.67
    however
    1.67
    despite
    1.65
    Activations Density 0.433%

    No Known Activations