© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59551
    Prev
    Next
    INDEX
    Explanations

    the [region] coast

    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
    언
    -0.85
    ```
    -0.84
     озеро
    -0.80
    喽
    -0.77
    芯
    -0.77
     Telugu
    -0.77
     média
    -0.76
    oxide
    -0.75
     dů
    -0.75
    Imprimir
    -0.75
    POSITIVE LOGITS
     coast
    3.34
     coastline
    2.25
     coasts
    2.11
    coast
    2.08
     shore
    1.95
     shores
    1.59
     Coast
    1.55
    海岸
    1.49
     COAST
    1.48
     côtes
    1.46
    Activations Density 0.039%

    No Known Activations