© 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. 74954
    Prev
    Next
    INDEX
    Explanations

    license information or total area

    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
    而后
    -1.29
     kapit
    -1.23
    álna
    -1.20
    اعات
    -1.18
    garanti
    -1.13
    徇
    -1.13
    ૮
    -1.12
    yship
    -1.10
    meability
    -1.09
     bús
    -1.08
    POSITIVE LOGITS
     is
    1.20
    apeno
    1.20
     calls
    1.17
     numbers
    1.10
     наличии
    1.10
     телефона
    1.10
     number
    1.05
    <bos>
    1.04
     phone
    1.03
     zamiast
    1.01
    Activations Density 0.001%

    No Known Activations