© 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. 93266
    Prev
    Next
    INDEX
    Explanations

    Next step or item

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

    The neuron detects discourse markers that introduce sequential steps or list items (e.g. “First,” “Next,” “Step,” “Up”).

    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
     ané
    -1.29
    鱨
    -1.28
     toks
    -1.17
    iments
    -1.16
    慑
    -1.14
    鳅
    -1.14
    adakan
    -1.13
     tabletas
    -1.12
    менти
    -1.11
    tión
    -1.10
    POSITIVE LOGITS
     Then
    1.60
     is
    1.20
     It
    1.17
    次に
    1.17
    次は
    1.16
    ,
    1.16
     Is
    1.16
     I
    1.15
    The
    1.12
     racconta
    1.11
    Activations Density 0.010%

    No Known Activations