© 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. 112984
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets

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

    the dot operator used to access object properties or methods in code.

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

    The neuron fires on the “.” token when used for object property or method access (dot‐notation member lookups).

    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
     The
    -1.86
     "
    -1.66
    .
    -1.59
    ).
    -1.59
    на
    -1.59
    </u>
    -1.52
     s
    -1.50
     After
    -1.46
    ;
    -1.45
     głównie
    -1.43
    POSITIVE LOGITS
    matitis
    1.81
     adecu
    1.77
    ſelves
    1.76
     proste
    1.75
     mesta
    1.75
    ＝＝＝＝
    1.73
     recepto
    1.73
     imun
    1.73
     indiví
    1.70
     inmun
    1.69
    Activations Density 0.029%

    No Known Activations