© 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. 12574
    Prev
    Next
    INDEX
    Explanations

    doing again

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

    The main thing this neuron does is detect numeric tokens (numbers or digits) 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
     bepaalde
    -1.05
    :[],
    -1.00
     ersten
    -0.96
     behandeling
    -0.94
     câncer
    -0.92
    erder
    -0.92
     verschillen
    -0.92
     (!_
    -0.91
    média
    -0.90
     infección
    -0.89
    POSITIVE LOGITS
     again
    3.75
     another
    2.81
    again
    2.44
    Again
    2.27
     erneut
    2.20
     AGAIN
    2.19
     Again
    2.11
    อีก
    2.09
     دوباره
    2.03
     novamente
    1.99
    Activations Density 0.043%

    No Known Activations