© 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. 34-GEMMASCOPE-RES-131K
    7. 89822
    Prev
    Next
    INDEX
    Explanations

    geographic locations and directions

    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
    ,—
    -0.93
    ábado
    -0.92
     resulting
    -0.91
    든
    -0.89
     necessary
    -0.89
    債
    -0.86
    größern
    -0.86
    鏝
    -0.84
    ubli
    -0.82
    ʑ
    -0.82
    POSITIVE LOGITS
     central
    2.25
     southern
    2.25
     southeastern
    2.19
     northern
    2.19
     southwestern
    2.14
     eastern
    2.13
     northwestern
    2.11
     western
    2.06
     the
    1.97
     northeastern
    1.97
    Activations Density 0.229%

    No Known Activations