© 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. 38779
    Prev
    Next
    INDEX
    Explanations

    code snippets and data fields

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

    The neuron spots code identifiers (especially CamelCase type or attribute names) in source code.

    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
     riman
    -0.97
    んでいる
    -0.95
    innocent
    -0.93
    kug
    -0.91
     notare
    -0.91
    ضح
    -0.90
     Hoffnung
    -0.88
    importante
    -0.88
    竟然是
    -0.88
    etched
    -0.86
    POSITIVE LOGITS
    אם
    1.12
    ristown
    1.10
    cibly
    1.10
    عالی
    1.09
    Aktualisiert
    1.08
    BOURNE
    1.08
     +
    1.06
    Якщо
    1.06
     crimen
    1.05
    arikat
    1.05
    Activations Density 0.004%

    No Known Activations