© 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. 33453
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and chemical groups

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

    mathematical expressions and notations, particularly those appearing in equations, formulas, and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects numerical tokens (digits, numeric constants, and related operators) in 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
     Ubicación
    -1.06
    completo
    -1.04
    camisetas
    -1.04
     Problemas
    -1.01
     Soporte
    -1.01
    Encontra
    -1.00
     Heilige
    -0.98
     Configuración
    -0.98
    になりますが
    -0.98
     komplet
    -0.97
    POSITIVE LOGITS
     at
    0.95
    🍂
    0.93
     Extragalactic
    0.92
    ),
    0.91
     као
    0.85
    турой
    0.85
     Melan
    0.84
     Pulver
    0.84
    ﻓ
    0.83
    </em>
    0.83
    Activations Density 0.001%

    No Known Activations