© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113866
    Prev
    Next
    INDEX
    Explanations

    xml artifactId

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

    the XML tag "artifactId" in Maven project configuration files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron flags unusually long tokens (i.e. words of roughly seven or more characters).

    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
    to
    -3.72
    $
    -3.36
    la
    -3.36
    If
    -3.25
    and
    -3.20
    It
    -3.17
    ra
    -3.09
    我
    -3.02
    ра
    -3.02
     If
    -2.98
    POSITIVE LOGITS
    淠
    3.91
    
    3.63
    
    3.33
    珰
    3.27
     撮り
    3.25
    葑
    3.25
    
    3.23
    神
    3.23
    〠
    3.20
    灤
    3.17
    Activations Density 0.003%

    No Known Activations