© 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. 14966
    Prev
    Next
    INDEX
    Explanations

    `(@` followed by variables

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

    The neuron fires on occurrences of the “@” symbol (e.g. in Twitter handles, code annotations, or function‐call syntax).

    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
     \
    -2.81
    /
    -2.70
     :
    -2.47
    2
    -2.34
     avec
    -2.31
    }
    -2.30
    ]
    -2.30
    '.
    -2.30
    _{
    -2.27
    。
    -2.23
    POSITIVE LOGITS
     serai
    2.55
     itſelf
    2.41
    ).”
    2.36
    ?”
    2.34
    坶
    2.25
    鬨
    2.17
    蕯
    2.13
     maquillage
    2.09
    section
    2.08
     boute
    2.08
    Activations Density 0.047%

    No Known Activations