© 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. 7650
    Prev
    Next
    INDEX
    Explanations

    LoRA, Temperature, liquid, entirely, repatriation

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

    This neuron strongly activates on blank‐line or paragraph‐break tokens (i.e. empty lines).

    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
    Ở
    1.01
    Ⲑ
    0.93
    𝙊
    0.93
     costituito
    0.91
    ມີ
    0.90
    spacePad
    0.90
    𒆜
    0.89
    𝙋
    0.88
     кількість
    0.85
     изпъл
    0.84
    POSITIVE LOGITS
    eren
    0.99
    st
    0.95
    ken
    0.94
    ize
    0.89
    ists
    0.88
    ss
    0.86
    es
    0.85
    ism
    0.85
    len
    0.85
    ssss
    0.85
    Activations Density 0.005%

    No Known Activations