© 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. 34-GEMMASCOPE-RES-131K
    4. 107356
    Prev
    Next
    INDEX
    Explanations

    named entities and their states

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

    This neuron activates on capitalized technical terms and acronyms (e.g., SVG, AI, CAM, CJD, ACS, COPD, SPR, PowerPoint) indicating it’s detecting domain-specific named entities.

    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
    多かった
    -1.46
     voltak
    -1.39
    )=>{
    
    -1.33
    ходили
    -1.33
    になるので
    -1.29
     vannak
    -1.28
    cuz
    -1.27
    ^{*},
    -1.26
     magnifiques
    -1.25
    になってしまう
    -1.25
    POSITIVE LOGITS
     is
    3.95
     has
    2.58
     isn
    2.30
     was
    2.22
     can
    2.14
     wasn
    1.84
     itself
    1.83
     shouldn
    1.71
     generally
    1.67
     cannot
    1.66
    Activations Density 0.404%

    No Known Activations