© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7225
    Prev
    Next
    INDEX
    Explanations

    license agreements

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

    The neuron detects license‐ and copyright‐header boilerplate blocks (e.g. license declarations) in source code comments.

    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
     from
    -1.41
     burgeoning
    -1.15
     took
    -1.14
     ellos
    -1.13
     what
    -1.13
     with
    -1.12
     även
    -1.11
     morgon
    -1.07
    그리고
    -1.06
     dessutom
    -1.06
    POSITIVE LOGITS
    訁
    1.42
     terrific
    1.28
     wonderful
    1.23
    ઃ
    1.20
    普通に
    1.17
    ढ़
    1.17
    owing
    1.16
     absurd
    1.16
     lauded
    1.16
     This
    1.15
    Activations Density 0.111%

    No Known Activations