© 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. 15865
    Prev
    Next
    INDEX
    Explanations

    noun phrases

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

    This neuron detects content‐bearing words in title‐case headings or multiword technical section titles.

    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
    6
    -1.29
     cooperativa
    -1.29
    8
    -1.23
    で
    -1.23
    を
    -1.22
    4
    -1.16
    そして
    -1.14
     vegano
    -1.14
    3
    -1.13
    ほか
    -1.12
    POSITIVE LOGITS
     its
    1.63
     their
    1.62
     magát
    1.47
    んだろう
    1.41
    -
    1.37
     például
    1.33
     Many
    1.32
    
    1.31
     często
    1.30
     három
    1.29
    Activations Density 0.166%

    No Known Activations