© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12656
    Prev
    Next
    INDEX
    Explanations

    technical code or explanation

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

    The neuron is triggered by numeric constants—particularly floating‐point numbers with 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
     didSet
    0.23
     json
    0.23
     yaml
    0.22
    ())
    0.22
     substring
    0.22
     tooltip
    0.21
     $("#
    0.21
     verbose
    0.21
     offsetX
    0.21
     ==
    0.21
    POSITIVE LOGITS
    industrie
    0.24
    agricultural
    0.19
    reliant
    0.18
     преимущественно
    0.18
    ړو
    0.18
    engineered
    0.17
    <unused622>
    0.17
     अल्को
    0.17
    <unused621>
    0.17
    fring
    0.17
    Activations Density 0.006%

    No Known Activations