© 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. 65643
    Prev
    Next
    INDEX
    Explanations

    social media platforms and links

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

    The neuron is primarily picking out tokens that contain digits—i.e. numerical sequences 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
    
    -1.09
     Alamy
    -1.04
     mechanism
    -1.03
    似乎
    -1.03
    owanego
    -1.02
     séries
    -1.01
     solution
    -1.01
     silla
    -1.00
     конфлик
    -1.00
     skol
    -0.99
    POSITIVE LOGITS
     Facebook
    1.53
     Twitter
    1.36
     on
    1.35
     and
    1.32
     Instagram
    1.30
     or
    1.17
     their
    1.14
     twitter
    1.13
     YouTube
    1.11
     email
    1.10
    Activations Density 0.013%

    No Known Activations