© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14984
    Prev
    Next
    INDEX
    Explanations

    explains or consequences

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

    Explanation of neuron 4 behavior: the main thing this neuron does is spot content words in long multi-sentence appreciative or testimonial‐style passages (the kind of praise/thanks language you see in comment spam).

    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
     TODAY
    0.87
    0.81
     stratég
    0.79
     strategic
    0.78
     today
    0.77
     recently
    0.75
     U
    0.75
     dnes
    0.74
     lately
    0.73
     dollars
    0.72
    POSITIVE LOGITS
    MoodAnalyser
    0.77
     যন্ত্রণা
    0.75
    ῃ
    0.75
     Zusätzlich
    0.73
    様子
    0.73
     воздей
    0.72
    webBrowser
    0.71
    AndroidJUnit
    0.70
     неё
    0.70
    Einstellungen
    0.70
    Activations Density 0.035%

    No Known Activations