© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69320
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

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

    The main thing this neuron does is find numeric literals (numbers, including integers and floats) 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_10/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
     where
    -1.72
     of
    -1.52
    ),”
    -1.50
     by
    -1.41
    ﻻ
    -1.40
    
    -1.38
     ardından
    -1.31
    ).”
    -1.31
    ická
    -1.30
     if
    -1.30
    POSITIVE LOGITS
    خبر
    1.43
     racconto
    1.42
     puisque
    1.42
    9
    1.41
    5
    1.40
     목록
    1.36
    饜
    1.30
     combustível
    1.29
     Fichier
    1.28
     esporte
    1.28
    Activations Density 0.000%

    No Known Activations