© 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. 10-GEMMASCOPE-RES-131K
    7. 130758
    Prev
    Next
    INDEX
    Explanations

    introduces explanation or consequence

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

    The neuron activates on the discourse transition word “So,” i.e. sentence-initial “So.”

    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
    r
    -1.60
    larda
    -1.54
    ván
    -1.48
     unidentified
    -1.47
    }}$
    -1.43
    所有
    -1.42
    尔
    -1.41
     всех
    -1.40
     plethora
    -1.39
    ž
    -1.38
    POSITIVE LOGITS
    дешь
    1.55
     technically
    1.52
     réalisateur
    1.49
     originalen
    1.47
     terá
    1.46
     ſome
    1.45
     conséquent
    1.44
     trente
    1.41
    隳
    1.41
     volvió
    1.38
    Activations Density 0.046%

    No Known Activations