© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2070
    Prev
    Next
    INDEX
    Explanations

    examples of scientific or technical writing

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

    The neuron fires on the very first content token at the start of each new section or paragraph.

    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
     sanciones
    0.77
    counts
    0.75
     நிதி
    0.74
    {}'.
    0.72
    '";
    0.71
    blica
    0.70
    OSED
    0.70
    🧹
    0.68
    essai
    0.68
    acher
    0.66
    POSITIVE LOGITS
     butyl
    0.89
     customized
    0.89
     Ayurvedic
    0.88
     aspirin
    0.88
     Ads
    0.85
     lut
    0.82
     hypogly
    0.80
     interferon
    0.79
     nutritious
    0.79
    anskrit
    0.79
    Activations Density 0.000%

    No Known Activations