© 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. 33711
    Prev
    Next
    INDEX
    Explanations

    Canada, estimates, much, 92ca1007

    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
     ingat
    -0.88
     Ministério
    -0.74
    Năm
    -0.73
     colina
    -0.71
    )}_{
    -0.70
     Luce
    -0.70
     dön
    -0.70
    –
    -0.69
     doubl
    -0.69
     mère
    -0.69
    POSITIVE LOGITS
     Schützen
    0.84
     agency
    0.81
     enlightening
    0.76
     enlighten
    0.75
    ault
    0.73
     advanced
    0.72
     passing
    0.71
     Information
    0.71
     Katzen
    0.71
    Lø
    0.71
    Activations Density 0.008%

    No Known Activations