© 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. 22-GEMMASCOPE-RES-131K
    7. 9299
    Prev
    Next
    INDEX
    Explanations

    roles, positions, and awards

    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_22/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
     the
    -1.44
     this
    -1.36
    −/−
    -1.35
    ’
    -1.31
    を行い
    -1.19
     unwarran
    -1.16
     The
    -1.14
     erfolgre
    -1.13
    定価
    -1.13
    総評
    -1.12
    POSITIVE LOGITS
    توضیحات
    1.25
    時間は
    1.23
    Spesifikasi
    1.22
    捗
    1.20
     documentos
    1.20
    تفسير
    1.18
     Préférences
    1.18
     zapatos
    1.18
    เคย
    1.15
    鼇
    1.14
    Activations Density 0.012%

    No Known Activations