© 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. 86948
    Prev
    Next
    INDEX
    Explanations

    ASC

    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
    Although
    -2.48
     時尚
    -2.42
     multitude
    -2.38
     οποία
    -2.30
     mythology
    -2.20
    ennessee
    -2.20
    تیجه
    -2.19
    
    -2.14
    臍
    -2.14
    tamientos
    -2.13
    POSITIVE LOGITS
    2
    3.09
    3
    2.66
    i
    2.64
    been
    2.59
    r
    2.45
    as
    2.41
    a
    2.39
    ‘
    2.39
     tetapi
    2.33
    ar
    2.31
    Activations Density 0.013%

    No Known Activations