© 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. 22-GEMMASCOPE-RES-131K
    7. 26851
    Prev
    Next
    INDEX
    Explanations

    looks like, of the

    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_22/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
     one
    -1.33
     will
    -1.13
    gridView
    -1.02
    kunta
    -0.97
     have
    -0.96
     high
    -0.96
    atecas
    -0.93
     quiet
    -0.93
     very
    -0.91
    tellten
    -0.90
    POSITIVE LOGITS
     gyóg
    1.01
     vrais
    1.01
     débat
    1.00
     montrant
    1.00
     Edad
    0.99
     laissant
    0.98
     fidèles
    0.98
    んだから
    0.96
     ordres
    0.96
     deixando
    0.96
    Activations Density 0.005%

    No Known Activations