© 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. 30447
    Prev
    Next
    INDEX
    Explanations

    license or version

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

    The neuron fires on numeric tokens (i.e. sequences of digits, including multi‐digit numbers or codes).

    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
     opinion
    -0.71
     поколения
    -0.69
     Paren
    -0.69
     Automata
    -0.69
    führende
    -0.68
     saúde
    -0.67
     Content
    -0.67
     parecen
    -0.66
     doenças
    -0.66
    otex
    -0.66
    POSITIVE LOGITS
     synchronization
    0.68
     MLS
    0.68
     النا
    0.66
     discussions
    0.65
    YMS
    0.64
    
    0.64
    Slide
    0.63
    BFF
    0.62
    郡
    0.62
     UIS
    0.61
    Activations Density 0.087%

    No Known Activations