© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    religious organizations or Christian principles

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

    The neuron is effectively a “position‐tracker” that fires strongly on tokens appearing very far along in a (long) input span, i.e. it detects when you’re near the end of a long document.

    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
    è
    0.75
    Breaking
    0.73
    tidak
    0.72
    К
    0.72
    كن
    0.71
    دو
    0.70
    з
    0.69
    в
    0.69
    كم
    0.68
     двор
    0.68
    POSITIVE LOGITS
    र्पण
    0.96
     wildfire
    0.89
    িশালী
    0.81
     antimony
    0.80
     नीचे
    0.77
     Uttarakhand
    0.77
     Peralta
    0.77
     Carab
    0.77
     Chlorine
    0.76
     unsubstituted
    0.76
    Activations Density 0.000%

    No Known Activations