© 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. 10-GEMMASCOPE-RES-131K
    7. 112019
    Prev
    Next
    INDEX
    Explanations

    without interest

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

    The main thing this neuron does is spot numeric expressions and measurements (numbers, dates, units, and related terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -1.21
     there
    -1.15
     its
    -1.13
    :
    -1.08
     continues
    -1.04
     intends
    -1.01
    勧め
    -1.00
     are
    -1.00
     prepares
    -1.00
     theirs
    -1.00
    POSITIVE LOGITS
    <tbody>
    1.24
    ủy
    1.23
     but
    1.19
    Namun
    1.17
     però
    1.17
     Therefore
    1.16
     magari
    1.13
     Câ
    1.12
    甚至是
    1.10
    Bahkan
    1.09
    Activations Density 0.116%

    No Known Activations