© 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. 4389
    Prev
    Next
    INDEX
    Explanations

    This neuron signals when the text is unusually long, activating strongly once the document has grown past a certain length.

    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
    ер
    1.01
    ヱ
    0.86
    '%
    0.80
    శా
    0.79
    г
    0.79
    ています
    0.76
     workforce
    0.75
    र
    0.75
     infarction
    0.74
    ている
    0.73
    POSITIVE LOGITS
     وأن
    1.11
     dotycz
    1.05
    smöglichkeiten
    0.95
    te
    0.94
     iż
    0.94
     należy
    0.92
     transpired
    0.91
    spro
    0.90
    संगिक
    0.90
    lerini
    0.89
    Activations Density 0.000%

    No Known Activations