© 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. 10-GEMMASCOPE-RES-131K
    7. 73962
    Prev
    Next
    INDEX
    Explanations

    URLs with query parameters

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

    The neuron specifically picks up question‐mark tokens (the “?” characters, e.g. in regexes or URL query strings).

    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
    }$,
    -2.39
    ﻒ
    -2.31
    ֮
    -2.17
     empfiehlt
    -2.16
    }$.
    -2.13
     You
    -2.03
     probabilmente
    -2.00
     vielleicht
    -2.00
    ]
    -1.98
    ◔
    -1.92
    POSITIVE LOGITS
    .
    2.47
    硨
    2.08
    塒
    2.02
    ほうが
    1.79
    ar
    1.77
    v
    1.76
     RELATION
    1.75
    ins
    1.72
     jackson
    1.71
    蕷
    1.71
    Activations Density 0.055%

    No Known Activations