© 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. 64702
    Prev
    Next
    INDEX
    Explanations

    distinguishes different items

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

    The neuron selectively activates on numeric tokens—especially standalone numbers (including decimals) that represent quantitative values or answer figures.

    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
    古风
    -1.11
     vital
    -1.03
    cuatro
    -1.01
    Ḱ
    -1.00
     on
    -0.98
    :''
    -0.98
     []
    -0.98
    yos
    -0.97
    এ
    -0.97
     atd
    -0.95
    POSITIVE LOGITS
     distintas
    1.26
    ↵↵
    1.26
     distintos
    1.25
     różnych
    1.19
     např
    1.14
     нагре
    1.09
    不同的
    1.08
     где
    1.05
     asesoramiento
    1.04
     énfasis
    1.04
    Activations Density 0.000%

    No Known Activations