© 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. 15283
    Prev
    Next
    INDEX
    Explanations

    investing decision information

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

    The neuron detects URL or file‐path fragments (e.g. tokens from web addresses, slashes, domains, and file names).

    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
     importantes
    0.77
    alin
    0.76
    ब
    0.75
    bere
    0.73
    icole
    0.70
     possibili
    0.69
    ari
    0.69
    合わせて
    0.69
     originales
    0.69
     capaces
    0.68
    POSITIVE LOGITS
    ค์
    0.82
    tiktok
    0.77
    Csv
    0.75
    뻤
    0.75
     Pét
    0.74
     GHz
    0.73
     MOSFET
    0.72
     Canva
    0.71
    MeshData
    0.71
    ですね
    0.70
    Activations Density 0.000%

    No Known Activations