© 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. 53813
    Prev
    Next
    INDEX
    Explanations

    yet to followed

    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
    面白い
    -1.06
    预计
    -1.04
     previously
    -1.02
     chaleco
    -1.01
     véhicules
    -1.00
     shopee
    -0.98
     możemy
    -0.98
    previously
    -0.97
     querem
    -0.96
     vrea
    -0.95
    POSITIVE LOGITS
     to
    3.58
     not
    1.22
     D
    1.11
     Even
    1.10
     S
    1.07
     Only
    0.98
     A
    0.95
     M
    0.95
     Actually
    0.94
     E
    0.94
    Activations Density 0.015%

    No Known Activations