© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    programming or code constructs

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

    The main thing this neuron does is detect mentions of legal wrongdoing or misconduct (e.g. misdemeanor charges).

    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
    pa
    0.86
    sh
    0.84
    st
    0.81
    ge
    0.81
    g
    0.77
    han
    0.76
    fl
    0.75
    ü
    0.75
    ut
    0.74
    hlt
    0.73
    POSITIVE LOGITS
    Ako
    0.82
     préoccup
    0.80
     liczb
    0.79
     модуля
    0.79
    替え
    0.78
    ﮗ
    0.78
    Ки
    0.78
     Auswahl
    0.75
     overshoot
    0.75
     fervent
    0.75
    Activations Density 0.000%

    No Known Activations