© 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. 34-GEMMASCOPE-RES-131K
    7. 90365
    Prev
    Next
    INDEX
    Explanations

    modern technology and terms

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

    This neuron responds to discourse‐structuring and transitional phrases (e.g. “For example,” “In essence,” “However,” “In order to”) commonly used in formal technical writing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    \}$.
    -1.16
    อะไร
    -0.92
    ніципалі
    -0.89
    鸷
    -0.89
    (',')
    -0.85
     יהיה
    -0.85
    +"_
    -0.85
    koľ
    -0.84
     després
    -0.84
     όπου
    -0.83
    POSITIVE LOGITS
     modern
    3.89
     newer
    3.13
    modern
    3.02
     modernen
    2.97
    Modern
    2.66
     современных
    2.66
     современ
    2.61
     moderne
    2.53
     nowoczes
    2.47
     Modern
    2.41
    Activations Density 0.289%

    No Known Activations