© 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. 34-GEMMASCOPE-RES-131K
    7. 33467
    Prev
    Next
    INDEX
    Explanations

    4069 or 4096

    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
     وزیر
    -0.94
     gordo
    -0.90
    胛
    -0.80
    🐅
    -0.80
    appId
    -0.79
    Kör
    -0.78
     pee
    -0.77
     edición
    -0.75
    nější
    -0.75
    Cô
    -0.75
    POSITIVE LOGITS
     toujours
    0.82
    ceries
    0.77
     heretics
    0.75
     Stück
    0.74
    epy
    0.72
    >'
    0.72
    стам
    0.71
    crats
    0.70
    shaped
    0.70
    ppi
    0.70
    Activations Density 0.032%

    No Known Activations