© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26841
    Prev
    Next
    INDEX
    Explanations

    BSD license and system calls

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

    This neuron detects source-code comment markers or header comment lines (e.g. “//”, “/*”, copyright/license headers).

    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
     Acesso
    -1.46
    おわりに
    -1.36
     Introducción
    -1.27
     Aluno
    -1.21
    ヤバ
    -1.20
     Tipos
    -1.19
     Japão
    -1.17
     Nedir
    -1.16
    无奈
    -1.16
     hoffen
    -1.16
    POSITIVE LOGITS
     but
    1.37
     it
    1.27
    mless
    1.24
     insumos
    1.21
     not
    1.20
    usions
    1.20
     use
    1.20
     after
    1.17
    warming
    1.17
     vermag
    1.16
    Activations Density 0.079%

    No Known Activations