© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7712
    Prev
    Next
    INDEX
    Explanations

    The neuron never activates on any tokens—it’s effectively “dead” and doesn’t detect any pattern.

    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
    ၈
    0.81
     Vé
    0.77
     thrones
    0.76
     बता
    0.74
     Crusaders
    0.74
    דיה
    0.71
     assail
    0.70
     Rangers
    0.69
    वेल
    0.68
     Waver
    0.68
    POSITIVE LOGITS
    ᄁ
    0.77
    iterate
    0.75
    ensia
    0.74
    怎樣
    0.72
    ens
    0.70
    sorted
    0.70
    ritional
    0.70
    ontaneous
    0.69
     dedans
    0.69
    rought
    0.68
    Activations Density 0.000%

    No Known Activations