© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    leaving or termination

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

    This neuron detects words and phrases that denote removing or excluding someone (e.g., suspension, banning, dropping, or kicking out).

    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
     snapshots
    0.75
     pilgrims
    0.70
     settlers
    0.69
     snapshot
    0.66
     l
    0.64
     (
    0.64
     lumen
    0.63
     i
    0.63
    0.63
     forgotten
    0.62
    POSITIVE LOGITS
     لأنه
    0.88
    porque
    0.88
     ética
    0.76
    Porque
    0.76
     должности
    0.74
    诽
    0.73
     BECAUSE
    0.73
    骂
    0.73
     поскольку
    0.71
     بسبب
    0.70
    Activations Density 0.009%

    No Known Activations