© 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. 34-GEMMASCOPE-RES-131K
    7. 63904
    Prev
    Next
    INDEX
    Explanations

    option, conditions, copyright

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

    The main thing this neuron does is detect numeric literals (digit sequences) in 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_34/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
     pauv
    -1.11
    例文帳に追加
    -1.06
     uſe
    -1.05
     finir
    -1.04
     trône
    -1.02
     durer
    -1.02
     bricola
    -1.02
     plafon
    -1.01
     meilleurs
    -1.01
     urat
    -0.99
    POSITIVE LOGITS
     While
    1.04
     JUST
    1.01
     T
    0.99
     Why
    0.98
     after
    0.98
     Surprisingly
    0.97
     Despite
    0.96
     F
    0.94
     A
    0.94
     t
    0.93
    Activations Density 0.004%

    No Known Activations