© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71765
    Prev
    Next
    INDEX
    Explanations

    progress and improvements

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

    The neuron detects numeric expressions and statistical values (digits, decimals, percentages, and other numbers) 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
     rekke
    -1.19
     would
    -1.13
    ülő
    -1.11
    Kích
    -1.11
     menyiapkan
    -1.09
     interesado
    -1.09
     pensaba
    -1.07
    之为
    -1.07
    ϳ
    -1.06
     montaje
    -1.05
    POSITIVE LOGITS
     improvements
    1.91
     improved
    1.71
     improvement
    1.69
     grâce
    1.48
     thanks
    1.40
     successes
    1.39
     progress
    1.35
     Improvements
    1.28
     success
    1.27
    のおかげ
    1.26
    Activations Density 0.097%

    No Known Activations