© 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. 102469
    Prev
    Next
    INDEX
    Explanations

    standard states and levels

    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_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
    父母
    -0.88
     regimen
    -0.83
     понима
    -0.82
     foray
    -0.82
     entire
    -0.81
     workday
    -0.81
     ilma
    -0.79
     notwendig
    -0.79
     &
    -0.79
     system
    -0.79
    POSITIVE LOGITS
    プション
    1.05
     amélior
    0.98
    listes
    0.93
     außerdem
    0.90
    anwalt
    0.90
     piensan
    0.90
     piden
    0.89
     hogy
    0.89
     moldes
    0.87
    Também
    0.86
    Activations Density 0.146%

    No Known Activations