© 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. 73093
    Prev
    Next
    INDEX
    Explanations

    $\mathbb{R}$, $\mathbb{C}$, $\mathbb{N}$

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

    This neuron fires on single capital-letter symbols in blackboard‐bold form (e.g. the “F,” “Q,” “Z,” “R,” “C,” etc. from \mathbb{…}).

    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
    骈
    -2.44
     dazzling
    -2.36
    tedì
    -2.33
     promotes
    -2.22
     Tieren
    -2.08
     achieves
    -2.06
    âmara
    -2.05
     resolute
    -2.05
                    
    -2.03
     ваше
    -2.03
    POSITIVE LOGITS
    and
    2.58
    蹰
    2.25
     Then
    2.19
    without
    2.19
    see
    2.17
    .!
    2.17
    ale
    2.13
    $
    2.09
    眼下
    2.09
    
    2.00
    Activations Density 0.006%

    No Known Activations