© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 738
    Prev
    Next
    INDEX
    Explanations

    This neuron activates strongly on negative auxiliary contractions (the “n’t”/’t tokens in words like don’t, isn’t, doesn’t).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    a
    0.52
    ی
    0.41
    en
    0.38
    an
    0.37
    o
    0.36
    ers
    0.36
    e
    0.36
    ি
    0.35
    ee
    0.35
     wondered
    0.34
    POSITIVE LOGITS
    任何
    0.62
     hề
    0.59
    丝毫
    0.58
    necessarily
    0.57
     necessarily
    0.53
     alcuna
    0.52
     alcun
    0.50
     necessariamente
    0.50
    任何人
    0.50
     obstante
    0.49
    Activations Density 0.620%

    No Known Activations