© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15710
    Prev
    Next
    INDEX
    Explanations

    measure or represents

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

    This neuron detects promotional or click-bait style content—tokens found in marketing calls-to-action and download/install instructions.

    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
    ---------------+
    0.57
     medicamento
    0.56
    服务
    0.53
     வேகமாக
    0.53
     ресур
    0.52
    股份
    0.52
     ক্লাব
    0.52
     médicament
    0.52
     pharmaceut
    0.52
     společnost
    0.52
    POSITIVE LOGITS
     yt
    0.54
     xưa
    0.54
    []
    0.53
     executing
    0.52
    sdf
    0.52
    Hover
    0.52
     executed
    0.51
    ုံး
    0.51
    ENER
    0.50
    ૈ
    0.50
    Activations Density 0.001%

    No Known Activations