© 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. 42164
    Prev
    Next
    INDEX
    Explanations

    artifact or artefacts

    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
    -
    -2.77
    of
    -2.53
     fluttering
    -2.25
     prioriti
    -2.13
    ot
    -2.13
     arduous
    -2.13
    ться
    -2.11
    ский
    -2.09
     =
    -2.06
    ของ
    -2.03
    POSITIVE LOGITS
     để
    2.53
    ’，
    2.41
    hamilan
    2.33
     να
    2.31
    _
    2.28
    ﮑ
    2.23
     sebut
    2.20
     Tudo
    2.20
     第三
    2.19
    Q
    2.17
    Activations Density 0.004%

    No Known Activations