© 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. 15625
    Prev
    Next
    INDEX
    Explanations

    starting sequences and base types

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

    This neuron fires on individual items in comma-separated lists (especially the list’s final element).

    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
    }^{\
    0.92
    }$,
    0.86
     REFERENCES
    0.86
     Epilepsy
    0.83
    بلی
    0.82
     exemplified
    0.81
     Acupuncture
    0.79
     Auschwitz
    0.79
     conformations
    0.79
     conceived
    0.78
    POSITIVE LOGITS
    ㈤
    0.86
     миру
    0.82
    ندية
    0.77
    本社
    0.77
    tonne
    0.77
    vano
    0.75
    soccer
    0.75
    រូប
    0.74
    nsan
    0.73
    ulter
    0.72
    Activations Density 0.001%

    No Known Activations