© 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. 95390
    Prev
    Next
    INDEX
    Explanations

    also, furthermore, likewise, in addition

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

    This neuron detects sentence-initial or clause-initial discourse markers signaling addition or continuation (e.g. “also,” “in addition,” “furthermore”).

    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
    rfan
    -1.01
     however
    -0.96
     from
    -0.96
    ētu
    -0.96
    orthand
    -0.90
     such
    -0.90
    رى
    -0.88
     jopa
    -0.88
     what
    -0.86
     "{\"
    -0.86
    POSITIVE LOGITS
     tampoco
    1.58
     नहीं
    1.27
     lacks
    1.14
     δεν
    1.12
     ไม่
    1.07
    ไม่ได้
    1.03
     never
    1.01
    也不
    1.01
     differs
    0.99
     nunca
    0.96
    Activations Density 0.036%

    No Known Activations