© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12549
    Prev
    Next
    INDEX
    Explanations

    synchrotron radiation, scripting, multifaceted approaches

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

    The neuron flags low‐frequency or out‐of-vocabulary token pieces—i.e. rare, lengthy, or domain-specific subwords.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atau
    -2.72
     {
    -2.33
     или
    -2.19
     квартира
    -2.11
     размере
    -2.03
     they
    -2.02
     November
    -1.99
     этими
    -1.98
     такими
    -1.95
     теми
    -1.95
    POSITIVE LOGITS
    媖
    3.14
    亊
    2.94
     髪型
    2.80
    🩻
    2.72
    戋
    2.72
    ጺ
    2.66
    휀
    2.59
    淠
    2.53
    )”
    2.47
    :”
    2.44
    Activations Density 0.004%

    No Known Activations