© 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. 22-GEMMASCOPE-RES-131K
    7. 66604
    Prev
    Next
    INDEX
    Explanations

    Here . maybe

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

    The main thing this neuron does is detect numeric tokens (especially numbers and measurements, including decimals).

    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
     mencionados
    -1.38
     разнообраз
    -1.38
     extremely
    -1.30
     Therefore
    -1.30
     данного
    -1.27
     весьма
    -1.25
    いかがでしたか
    -1.22
    了我
    -1.21
     retrovisor
    -1.21
     чрезвы
    -1.20
    POSITIVE LOGITS
     maybe
    1.44
    nadequate
    1.36
     easy
    1.20
    Ḳ
    1.19
    leqslant
    1.18
    . 
    1.16
     irgendwann
    1.16
     "','
    1.16
    ጴ
    1.13
    żo
    1.11
    Activations Density 0.019%

    No Known Activations