© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7231
    Prev
    Next
    INDEX
    Explanations

    names, prices, characters

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

    The main thing this neuron does is flag tokens that produce abnormally large, outlier activation spikes (i.e. rare or anomalous tokens triggering extremely high values).

    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
    da
    1.01
    de
    0.86
    ds
    0.85
    र
    0.83
    "
    0.83
    th
    0.82
    م
    0.77
    cm
    0.74
    m
    0.73
    خ
    0.72
    POSITIVE LOGITS
     nở
    1.13
     legales
    1.07
     navegador
    1.05
     sinner
    1.03
     recuer
    1.02
     locais
    1.00
     recuerdo
    0.99
     variável
    0.98
     andar
    0.98
     ricordo
    0.96
    Activations Density 0.000%

    No Known Activations