© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91662
    Prev
    Next
    INDEX
    Explanations

    abstracted concepts and art

    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
     militari
    -0.95
     Anſ
    -0.94
     CIVIL
    -0.94
     produire
    -0.93
    omości
    -0.90
     ACTIV
    -0.88
     diſt
    -0.87
     numerus
    -0.87
     tentando
    -0.86
     aprobación
    -0.85
    POSITIVE LOGITS
     create
    1.16
     or
    1.05
     reasoning
    1.03
     garner
    1.03
     concepts
    1.03
     focusing
    1.02
     painting
    1.01
     expression
    1.00
    ing
    1.00
     placing
    0.99
    Activations Density 0.017%

    No Known Activations