© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66910
    Prev
    Next
    INDEX
    Explanations

    prefixes for specific words or phrases

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

    The neuron fires on programming or code‐related tokens (e.g. function names and technical terms).

    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
    still
    -1.24
    raught
    -1.04
     方法
    -1.00
     its
    -0.99
    Still
    -0.99
    zegor
    -0.98
     gafas
    -0.97
     przeds
    -0.96
    ofType
    -0.94
    bagian
    -0.94
    POSITIVE LOGITS
    らしい
    0.99
    әһ
    0.92
     defending
    0.92
     Weltkrieg
    0.89
     papal
    0.89
    Convey
    0.88
    setMsg
    0.88
     Кубка
    0.88
    ‌لار
    0.88
     obligatory
    0.88
    Activations Density 0.000%

    No Known Activations