© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 258356
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     દવા
    0.58
     Plusieurs
    0.54
     이벤트
    0.54
     ilaç
    0.53
     섹
    0.53
     ਨ
    0.52
     ११
    0.52
     скла
    0.52
     بإ
    0.51
     아직
    0.51
    POSITIVE LOGITS
    ():
    0.50
     qualifying
    0.48
     graphically
    0.48
     yearning
    0.47
     schematic
    0.46
     longing
    0.46
    QE
    0.46
     modern
    0.45
     biographical
    0.44
     vision
    0.44
    Activations Density 0.001%

    No Known Activations