© 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. 34-GEMMASCOPE-RES-131K
    7. 82456
    Prev
    Next
    INDEX
    Explanations

    percentage changes and values

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

    The neuron detects numeric tokens—especially digits and percent‐signs in statistical or quantitative expressions.

    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
     of
    -1.87
    ของ
    -1.29
    extAlignment
    -0.96
     của
    -0.93
     edifici
    -0.91
    糴
    -0.88
     των
    -0.88
     vastly
    -0.88
     giù
    -0.86
    ERI
    -0.84
    POSITIVE LOGITS
     in
    1.19
     during
    1.16
     from
    1.13
     while
    1.05
     compared
    0.97
     Erhöhung
    0.96
     to
    0.93
     percent
    0.91
     gunakan
    0.91
     more
    0.91
    Activations Density 0.036%

    No Known Activations