© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26587
    Prev
    Next
    INDEX
    Explanations

    Chief Keef, any state, Q:, 1

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

    The neuron detects structured list elements—especially numbered or bullet‐style items and their headings in formal/legal documents.

    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
     this
    -2.22
     using
    -1.92
     on
    -1.92
     first
    -1.90
     all
    -1.89
     from
    -1.89
     at
    -1.88
     you
    -1.80
     by
    -1.77
     it
    -1.62
    POSITIVE LOGITS
     turmoil
    1.66
     Dinas
    1.65
     .......
    1.64
     startling
    1.60
     isolamento
    1.56
    actually
    1.55
    取决
    1.55
    generally
    1.54
    ඍ
    1.53
     REALLY
    1.51
    Activations Density 0.002%

    No Known Activations