© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 137
    Prev
    Next
    INDEX
    Explanations

    Central Asian place names

    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
     ingat
    -1.02
    dersfield
    -0.97
    Jamaica
    -0.96
    泾
    -0.93
     motore
    -0.93
     futbolista
    -0.93
     terrorismo
    -0.93
    حياتها
    -0.93
     kutu
    -0.93
     satria
    -0.92
    POSITIVE LOGITS
    ouchable
    1.06
     hivyo
    1.06
     kawaida
    1.01
    а
    1.01
     ndani
    1.00
     robić
    1.00
     wszyscy
    1.00
     на
    0.96
    ||}
    0.96
     этот
    0.96
    Activations Density 0.028%

    No Known Activations