© 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. 9798
    Prev
    Next
    INDEX
    Explanations

    relationships between concepts

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

    This neuron consistently lights up on the final token of a text segment, effectively marking the end of a paragraph or block.

    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
     со
    0.65
    twilio
    0.62
     э
    0.62
     কল
    0.61
     সাং
    0.59
     sai
    0.59
     vi
    0.59
     experiential
    0.59
     interactive
    0.59
     christian
    0.58
    POSITIVE LOGITS
    ClFN
    0.98
    楤
    0.87
    Prothorax
    0.87
    cuando
    0.86
    ACING
    0.86
     Высо
    0.86
     outcrops
    0.84
     mój
    0.84
    विस
    0.81
     поверхность
    0.80
    Activations Density 0.000%

    No Known Activations