© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19072
    Prev
    Next
    INDEX
    Explanations

    transitions or implications

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

    The neuron specializes in spotting LaTeX arrow commands (e.g. “\longrightarrow”, “\Longleftrightarrow”) within mathematical expressions.

    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
    Although
    -3.27
    Despite
    -3.13
    Since
    -3.05
    There
    -3.02
    The
    -2.97
    Because
    -2.92
    With
    -2.92
    While
    -2.84
    During
    -2.78
    After
    -2.75
    POSITIVE LOGITS
    ↵
    4.28
    髕
    3.11
    ’
    3.03
    怎样的
    2.70
    许久
    2.67
    .
    2.63
     —
    2.53
    鸶
    2.52
    the
    2.48
    僰
    2.45
    Activations Density 0.001%

    No Known Activations