© 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. 10-GEMMASCOPE-RES-131K
    4. 47587
    Prev
    Next
    INDEX
    Explanations

    place names and landmarks

    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_10/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
    --"
    -2.05
    }
    -2.02
    ...
    -1.77
    -
    -1.76
     merkwür
    -1.75
    鼕
    -1.73
    '
    -1.68
     pueda
    -1.68
    鹦
    -1.63
     besonder
    -1.61
    POSITIVE LOGITS
    as
    2.30
    sellors
    2.16
    有三
    2.11
     of
    2.09
    dzić
    2.03
    咨
    2.03
    玙
    2.02
     dahulu
    1.98
    lden
    1.94
     teritor
    1.93
    Activations Density 0.014%

    No Known Activations