© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12933
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with frac

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    el
    -1.11
    monix
    -1.07
     both
    -1.07
    os
    -1.05
     group
    -1.03
    "
    -1.02
    '''
    -1.00
    s
    -1.00
     jPanel
    -1.00
    millimeters
    -1.00
    POSITIVE LOGITS
    Leírás
    1.46
    Besos
    1.39
    Slik
    1.30
    Tentang
    1.25
    Suerte
    1.20
    Wady
    1.19
    Bety
    1.18
    
    1.18
    Suka
    1.18
    Alles
    1.17
    Activations Density 0.025%

    No Known Activations