© 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. 31-GEMMASCOPE-2-RES-16K
    4. 8088
    Prev
    Next
    INDEX
    Explanations

    European Parliament Elections

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

    The neuron specifically detects list‐item bullet markers (the “•” characters) in the text.

    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_31_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
     glTex
    0.64
     кнопки
    0.62
    😨
    0.61
     psor
    0.61
    ☃
    0.61
     ><
    0.60
     nunca
    0.58
     messed
    0.58
    😭😭
    0.58
    😺
    0.57
    POSITIVE LOGITS
    tevõ
    0.69
     Remembrance
    0.66
     ADB
    0.61
     ”
    0.59
     लैस
    0.58
     exclusionary
    0.56
     observance
    0.55
     Energy
    0.55
     कब्जा
    0.55
     समझौता
    0.55
    Activations Density 0.000%

    No Known Activations