© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39841
    Prev
    Next
    INDEX
    Explanations

    one or, required by

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

    This neuron activates on the boilerplate licensing header—specifically the “Licensed to … under one or more contributor license agreements” phrasing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     unicórnio
    -1.34
     konsek
    -1.24
     Fils
    -1.23
     Données
    -1.20
    xvii
    -1.19
    ℅
    -1.19
     tatuaje
    -1.18
     silnika
    -1.17
     boxeo
    -1.17
     cuchillo
    -1.16
    POSITIVE LOGITS
    vantaged
    1.34
    は
    1.24
    軌
    1.14
    所以在
    1.09
    があるので
    1.05
    помним
    1.04
     poussière
    1.02
    がありますが
    1.02
     школа
    1.01
    <bos>
    0.99
    Activations Density 0.530%

    No Known Activations