© 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. 10-GEMMASCOPE-RES-131K
    7. 45254
    Prev
    Next
    INDEX
    Explanations

    allow, enable, or disallow options

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

    This neuron fires on configuration‐style option names or flags in code (e.g. allowInvalidCertificates, allowAwaitOutsideFunction, allowJs, 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_10/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
     The
    -1.41
     our
    -1.33
     Verwenden
    -1.27
     вполне
    -1.25
     vermutlich
    -1.24
    éri
    -1.23
    ];
    -1.23
    ではない
    -1.22
     didn
    -1.21
     keluarganya
    -1.20
    POSITIVE LOGITS
     statistiques
    1.44
     evenement
    1.42
    archical
    1.41
    Its
    1.39
     gants
    1.35
     AQUÍ
    1.31
     lourdes
    1.30
     jupe
    1.30
    ḿ
    1.29
    
    1.27
    Activations Density 0.063%

    No Known Activations