© 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. 34-GEMMASCOPE-RES-131K
    7. 106731
    Prev
    Next
    INDEX
    Explanations

    matters presented as following

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

    This neuron detects the standard condition‐clause wording in open-source license boilerplate (e.g. “provided that the following conditions are met”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    那里
    -0.94
    来歴
    -0.88
     dasselbe
    -0.84
    那就是
    -0.84
     aqueles
    -0.84
    それが
    -0.79
    رش
    -0.79
     Unterrichts
    -0.79
     a
    -0.78
    そういう
    -0.78
    POSITIVE LOGITS
     the
    3.45
     following
    3.05
    以下
    2.56
     folgende
    2.52
     følgende
    2.47
     následu
    2.44
     следующие
    2.27
     seguinte
    2.22
    以下の
    2.22
     siguiente
    2.22
    Activations Density 0.407%

    No Known Activations