© 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. 1587
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on unusually rare or high-index vocabulary tokens.

    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
    V
    0.74
    Tapi
    0.72
    вет
    0.72
    H
    0.68
    Dispose
    0.66
    F
    0.62
     Ecosystem
    0.62
    B
    0.62
    P
    0.60
     بی‌
    0.59
    POSITIVE LOGITS
     Faktoren
    0.84
     okula
    0.82
    जनन
    0.81
     dinding
    0.79
     kommt
    0.77
     sucht
    0.76
    न्द्र
    0.76
    बिनेट
    0.75
     voltou
    0.75
     خرا
    0.75
    Activations Density 0.000%

    No Known Activations