© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95843
    Prev
    Next
    INDEX
    Explanations

    identifying technical information

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

    The neuron fires on fully‐qualified Java package and class names (e.g. import java.* or java.util.jar.Manifest).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    睹
    -1.01
     livro
    -0.96
     ของ
    -0.93
     secolo
    -0.91
    Ȣ
    -0.90
     برای
    -0.89
     Krzysz
    -0.89
     unnatural
    -0.86
    ötzlich
    -0.86
    retion
    -0.84
    POSITIVE LOGITS
     information
    1.39
    info
    1.13
     identifying
    1.02
     info
    1.01
     about
    0.99
     several
    0.93
     branding
    0.92
    Identity
    0.91
     Information
    0.89
    Info
    0.89
    Activations Density 0.161%

    No Known Activations