© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68478
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     patata
    -1.18
     primas
    -1.07
     industria
    -1.05
    ğum
    -1.03
     its
    -1.02
     policia
    -1.02
     vocal
    -1.02
     habile
    -1.00
     outros
    -1.00
     kuid
    -0.99
    POSITIVE LOGITS
     essenziale
    0.98
    惩
    0.97
    Lise
    0.96
     Sortiment
    0.95
     estremamente
    0.95
    Cada
    0.95
     culoare
    0.94
    Laos
    0.94
    Moda
    0.93
     sàn
    0.92
    Activations Density 0.001%

    No Known Activations