© 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. 22-GEMMASCOPE-RES-131K
    7. 33800
    Prev
    Next
    INDEX
    Explanations

    math operators and variables

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

    The neuron is detecting numerical tokens (digits and numeric constants) 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_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
    Kommentare
    -1.09
     corrom
    -1.02
    Farbe
    -1.02
    iligt
    -0.97
    iações
    -0.93
    ategorie
    -0.93
    Ajust
    -0.92
    entrevista
    -0.92
    Funktionen
    -0.92
     rarement
    -0.91
    POSITIVE LOGITS
     along
    1.02
     from
    0.99
     Nx
    0.96
    )
    0.90
    THE
    0.90
    SystemColors
    0.88
     together
    0.88
     kasama
    0.85
     vänner
    0.83
     every
    0.82
    Activations Density 0.083%

    No Known Activations