© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66628
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and definitions

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

    This neuron detects the instructional, step‐by‐step explanatory language typically used in math or technical solution write-ups.

    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
    ִּ
    -1.52
     or
    -1.27
     not
    -1.27
     PLAINT
    -1.27
     without
    -1.19
     of
    -1.19
     tier
    -1.17
    וּ
    -1.16
    batsman
    -1.16
     based
    -1.16
    POSITIVE LOGITS
     religieuses
    1.84
    ֩
    1.58
     we
    1.58
     chré
    1.49
     religieux
    1.47
     растений
    1.47
     стихотво
    1.44
    JECT
    1.42
     supérieures
    1.37
     AMAZING
    1.36
    Activations Density 0.048%

    No Known Activations