© 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. 48200
    Prev
    Next
    INDEX
    Explanations

    quantum computing and quantum mechanics

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

    the mentions of “quantum” (and closely related technical quantum‐computing terms).

    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
     получила
    -1.44
    cosystem
    -1.34
     quedó
    -1.33
    
    -1.30
    ceis
    -1.24
     will
    -1.22
     JTextArea
    -1.21
     Auftritt
    -1.20
    Such
    -1.18
     takich
    -1.16
    POSITIVE LOGITS
     argentinos
    1.32
    呖
    1.27
     casero
    1.25
    私に
    1.23
    タカ
    1.22
    任何人
    1.21
    ffa
    1.19
     ceremonies
    1.16
    gehen
    1.16
     Knives
    1.16
    Activations Density 0.091%

    No Known Activations