© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117167
    Prev
    Next
    INDEX
    Explanations

    equations, choose, suppose, is

    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
     ¬
    -0.99
     bayer
    -0.97
    Satis
    -0.97
    会导致
    -0.97
     proofing
    -0.95
    Hrsg
    -0.94
    ℴ
    -0.93
    Analytical
    -0.92
    ceedings
    -0.89
     CERN
    -0.88
    POSITIVE LOGITS
     verdura
    0.95
     happiness
    0.94
    ανε
    0.93
     estrategias
    0.92
     ideas
    0.90
    ISES
    0.88
     funguje
    0.88
     mengapa
    0.87
    ändigt
    0.86
    াজ
    0.86
    Activations Density 0.264%

    No Known Activations