© 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. 34855
    Prev
    Next
    INDEX
    Explanations

    SQL queries and code structures

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

    The neuron fires on non-standard “word” tokens—digits, symbols, punctuation, and code-like uppercase or numeric tokens.

    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
     existing
    -1.16
     aspetto
    -1.14
    ?
    -1.10
    喏
    -1.09
     recommandée
    -1.05
     inoltre
    -1.05
    Iné
    -1.05
    ↵↵↵
    -1.04
     actuelle
    -1.02
     существу
    -1.02
    POSITIVE LOGITS
    </i>
    1.19
    </em>
    1.15
    </b>
    1.05
    薗
    1.01
     Володи
    0.96
     matchs
    0.94
    )
    0.94
    眉头
    0.91
     beaux
    0.91
     finition
    0.90
    Activations Density 0.204%

    No Known Activations