© 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. 3091
    Prev
    Next
    INDEX
    Explanations

    licensed under Notice

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

    This neuron fires on license‐header boilerplate (copyright years and licensing terms like “Licensed under the Apache License,” “the,” etc.).

    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
     its
    -1.54
     their
    -1.34
     should
    -1.17
     several
    -1.07
     both
    -1.04
     gedung
    -1.01
     those
    -1.01
     there
    -0.99
     three
    -0.98
     this
    -0.95
    POSITIVE LOGITS
    gande
    1.01
    <blockquote>
    0.93
    蝋
    0.91
    ፫
    0.90
    сила
    0.90
    particularly
    0.90
    UAGES
    0.90
     коли
    0.89
     deose
    0.89
    KU
    0.89
    Activations Density 0.296%

    No Known Activations