© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69383
    Prev
    Next
    INDEX
    Explanations

    into followed by something

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

    This neuron detects phrases that express reluctance to provide excessive detail—e.g. “going into too much graphic detail.”

    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
     when
    -2.73
     but
    -2.05
     then
    -1.94
     because
    -1.86
     not
    -1.59
     nên
    -1.48
     with
    -1.45
     only
    -1.36
     before
    -1.34
    뿐
    -1.32
    POSITIVE LOGITS
     the
    1.59
     réjou
    1.48
     komplet
    1.34
    ೢ
    1.32
    Gön
    1.30
     inolvid
    1.29
     erreur
    1.28
     mensen
    1.28
     opérateur
    1.26
     décro
    1.25
    Activations Density 0.110%

    No Known Activations