© 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. 552
    Prev
    Next
    INDEX
    Explanations

    names with romanized East Asian syllables

    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
     and
    -1.64
     vertes
    -1.20
     kalah
    -1.20
     kong
    -1.20
     musli
    -1.19
     موبایل
    -1.18
     gelb
    -1.17
     minne
    -1.17
     matematika
    -1.16
     januar
    -1.13
    POSITIVE LOGITS
     latter
    1.39
    P
    1.27
    都是在
    1.20
    C
    1.17
    y
    1.15
     Сейчас
    1.13
     offiziellen
    1.11
    E
    1.10
    T
    1.10
     alcune
    1.10
    Activations Density 0.015%

    No Known Activations