© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65860
    Prev
    Next
    INDEX
    Explanations

    closing markdown links or section IDs

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

    This neuron detects numeric counts or sizes that appear alongside headings, links, or filenames (e.g. section numbers or file‐size annotations).

    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
    
    -1.63
     Coloque
    -1.45
     keramik
    -1.41
     klient
    -1.39
    ſelf
    -1.38
     paraíso
    -1.37
     didik
    -1.37
     Escribe
    -1.36
     mikina
    -1.36
     triko
    -1.36
    POSITIVE LOGITS
    ↵↵
    1.52
     and
    1.52
     V
    1.38
     F
    1.36
     C
    1.36
     D
    1.34
     K
    1.34
    </h2>
    1.27
     S
    1.27
     T
    1.27
    Activations Density 0.005%

    No Known Activations