© 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. 10-GEMMASCOPE-RES-131K
    7. 127382
    Prev
    Next
    INDEX
    Explanations

    locations followed by county 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_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
    """
    -1.73
    its
    -1.63
    if
    -1.63
    with
    -1.61
    媖
    -1.54
                    
    -1.47
    vió
    -1.47
    й
    -1.45
    蛧
    -1.44
     niña
    -1.43
    POSITIVE LOGITS
    ↵↵
    2.02
    jaqueta
    1.95
    後記
    1.66
    偁
    1.63
     アレンジ
    1.50
    obt
    1.49
    mId
    1.49
     stihl
    1.48
    [?]
    1.48
     外観
    1.47
    Activations Density 0.112%

    No Known Activations