© 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. 54300
    Prev
    Next
    INDEX
    Explanations

    geographical locations and personal identifiers

    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
     taba
    -1.15
     mitra
    -1.12
    🥘
    -1.05
     alfab
    -1.02
     ekos
    -1.01
     bello
    -1.00
     bakar
    -0.99
     balas
    -0.98
     morfo
    -0.98
     to
    -0.97
    POSITIVE LOGITS
    Hilsen
    1.42
     your
    1.38
    Análisis
    1.25
     juzgar
    1.24
     aislados
    1.21
     amelyek
    1.19
    ῖς
    1.18
    Slik
    1.18
    NewLabel
    1.16
     you
    1.13
    Activations Density 0.001%

    No Known Activations