© 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. 22-GEMMASCOPE-RES-131K
    7. 104454
    Prev
    Next
    INDEX
    Explanations

    we can calculate

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

    This neuron detects the discourse markers and first-person plural formulations that introduce and structure step-by-step mathematical solution explanations.

    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
    mengen
    -1.16
     todas
    -1.11
     slika
    -1.10
    nyata
    -1.09
    resultados
    -1.09
    вгений
    -1.09
     logotipo
    -1.08
    karakter
    -1.07
    inspira
    -1.07
    mutter
    -1.07
    POSITIVE LOGITS
     our
    1.10
    N
    1.03
     yong
    1.02
     then
    1.02
     but
    0.99
     itong
    0.97
    ://$
    0.96
    噻
    0.93
    its
    0.93
     pollut
    0.93
    Activations Density 0.011%

    No Known Activations