© 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. 34368
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, currency, days

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

    The neuron is primarily detecting numeric tokens (numbers) in the text.

    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
     ས
    -1.20
     enfermera
    -1.18
    鸰
    -1.15
     humeur
    -1.13
     موسي
    -1.10
    やろ
    -1.09
     ملابس
    -1.09
     prakti
    -1.09
     rapporter
    -1.08
    jangkau
    -1.07
    POSITIVE LOGITS
     vaikka
    1.26
    Bioaccumulative
    1.13
    通常
    1.11
     löyty
    1.10
    의
    1.09
    нибудь
    1.08
    默认为
    1.07
     ausdrücklich
    1.07
    至少
    1.03
    </tbody>
    1.01
    Activations Density 0.018%

    No Known Activations