© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11095
    Prev
    Next
    INDEX
    Explanations

    time prepositions and determiners

    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
    感じが
    -1.59
     новых
    -1.51
    気がする
    -1.44
     coraggio
    -1.43
     profondo
    -1.40
     ſec
    -1.38
    鶺
    -1.34
     encontró
    -1.33
    気がします
    -1.33
     dubbio
    -1.32
    POSITIVE LOGITS
    ’
    1.30
     Grüßen
    1.27
    чия
    1.27
     européen
    1.24
    ~♪
    1.18
    ที่
    1.18
     összefoglal
    1.17
    「
    1.16
    ・・。
    1.16
    海苔
    1.15
    Activations Density 0.092%

    No Known Activations