© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    ending code or lists

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

    The neuron is detecting floating‐point numeric values (numbers containing decimal points).

    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
     איז
    0.82
    ਕ
    0.81
    äischen
    0.81
     প্রবন্ধে
    0.80
    ী
    0.77
     მე
    0.76
    benhav
    0.76
    gna
    0.75
     кандай
    0.75
    aulay
    0.74
    POSITIVE LOGITS
    ով
    0.71
     landmarks
    0.71
    ,
    0.70
     staples
    0.69
    梧
    0.69
    1
    0.68
     totaling
    0.68
    围绕
    0.67
     spie
    0.67
    炽
    0.67
    Activations Density 0.004%

    No Known Activations