© 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. 13268
    Prev
    Next
    INDEX
    Explanations

    profitable investing stocks

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

    The neuron strongly responds to uncommon or low‐frequency tokens (i.e. “rare” words).

    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
    sion
    0.77
    lian
    0.70
    iert
    0.68
    ó
    0.66
    न्थ
    0.65
    نين
    0.65
     Carbon
    0.64
    EG
    0.62
    sley
    0.62
    عت
    0.61
    POSITIVE LOGITS
    備
    0.84
     mitä
    0.83
     하지
    0.83
     отмеча
    0.82
     갔
    0.80
    쇠
    0.80
    อะไร
    0.79
     університе
    0.79
     anisotrop
    0.79
    ✷
    0.79
    Activations Density 0.001%

    No Known Activations