© 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. 123746
    Prev
    Next
    INDEX
    Explanations

    country Indonesia

    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
    </i>
    -3.33
    -3.19
    他的
    -3.14
    9
    -3.09
    1
    -3.03
    7
    -2.95
     "
    -2.94
    0
    -2.88
    8
    -2.88
    3
    -2.86
    POSITIVE LOGITS
    .
    3.31
    脔
    3.05
    媗
    2.88
    .《
    2.63
    狆
    2.59
    柃
    2.58
    “.
    2.53
    farers
    2.47
    “)
    2.41
    farer
    2.41
    Activations Density 0.002%

    No Known Activations