© 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. 104186
    Prev
    Next
    INDEX
    Explanations

    form or language text

    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
    
    -2.59
    结语
    -2.33
    んびり
    -2.28
    Ꮚ
    -2.27
     acrílico
    -2.23
    数据的
    -2.16
     parachoque
    -2.14
    いろんな
    -2.14
    ことにしました
    -2.14
     využí
    -2.13
    POSITIVE LOGITS
     we
    2.89
     Then
    2.81
    en
    2.41
     are
    2.23
     about
    2.19
    of
    2.17
    ’
    2.14
    as
    2.02
     fabulous
    1.97
     Regarding
    1.91
    Activations Density 0.001%

    No Known Activations