© 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. 92895
    Prev
    Next
    INDEX
    Explanations

    software project names

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

    This neuron detects code‐header/license blocks by spotting project/library names, version identifiers, copyright years, and related tokens in source‐file 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
    During
    -0.95
     posiada
    -0.91
    Other
    -0.88
     conocidas
    -0.83
     остальных
    -0.82
     alebo
    -0.80
    relser
    -0.80
    Šalt
    -0.79
    Knowing
    -0.79
    先は
    -0.79
    POSITIVE LOGITS
     project
    1.69
     Project
    1.55
    Project
    1.45
     Projekt
    1.42
     projeto
    1.39
     Consortium
    1.32
    project
    1.28
     پروژه
    1.24
    プロジェクト
    1.24
     PROJECT
    1.23
    Activations Density 0.281%

    No Known Activations