© 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. 12334
    Prev
    Next
    INDEX
    Explanations

    ASCII art elements

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

    The neuron is triggered by numeric tokens—dates, times, list or section numbers, and other digit sequences.

    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
    <unused2156>
    0.57
     burlap
    0.56
    <unused5>
    0.55
     steadfast
    0.55
    <unused85>
    0.54
     αυτή
    0.54
     féidir
    0.54
    बैक
    0.54
    <unused12>
    0.53
     HIPAA
    0.53
    POSITIVE LOGITS
    former
    0.59
    ↵↵
    0.58
    ↵↵↵
    0.57
    Ang
    0.56
       
    0.53
    ↵
    0.52
    OUSE
    0.51
    <start_of_image>
    0.51
                
    0.51
    tiny
    0.51
    Activations Density 0.025%

    No Known Activations