© 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. 34-GEMMASCOPE-RES-131K
    4. 109347
    Prev
    Next
    INDEX
    Explanations

    cardinal directions followed by of

    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
     combustível
    -0.98
     случаях
    -0.97
    ﮦ
    -0.94
     lyder
    -0.93
    Bibliografie
    -0.91
     licencias
    -0.91
     camiones
    -0.90
    tholes
    -0.90
    alamualaikum
    -0.90
     cómoda
    -0.89
    POSITIVE LOGITS
     of
    6.56
    ของ
    2.06
     của
    2.03
     from
    1.55
    of
    1.51
     των
    1.33
     Of
    1.31
     της
    1.17
     של
    1.14
     ऑफ
    1.14
    Activations Density 0.023%

    No Known Activations