© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7048
    Prev
    Next
    INDEX
    Explanations

    ec2 actions

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

    The neuron spotlights technical resource identifiers—things like registry key paths, URLs, package/module namespaces, and similar structured configuration or code‐reference strings.

    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_31_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
     ເ
    0.58
     ince
    0.58
     Belgrade
    0.57
     dumbbells
    0.57
     sits
    0.56
     între
    0.56
     Berat
    0.55
     éstas
    0.55
     yüz
    0.54
    🕺
    0.54
    POSITIVE LOGITS
    javax
    0.92
    Microsoft
    0.89
     javax
    0.87
    androidx
    0.83
     com
    0.79
    microsoft
    0.76
     androidx
    0.74
     microsoft
    0.74
    jetbrains
    0.74
     org
    0.72
    Activations Density 0.042%

    No Known Activations