© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    superconducting materials and phenomena

    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
    ia
    -1.86
    us
    -1.77
    ing
    -1.59
    ti
    -1.51
    is
    -1.51
    essive
    -1.43
     remembrance
    -1.43
    빠
    -1.42
    蛆
    -1.41
    ;-
    -1.39
    POSITIVE LOGITS
     EVER
    1.67
     exhibiting
    1.65
     WAY
    1.58
    豨
    1.52
     heading
    1.50
    ÓN
    1.43
    bitkan
    1.38
    wość
    1.37
     respected
    1.34
     utilizing
    1.34
    Activations Density 0.051%

    No Known Activations