© 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. 67316
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and serials

    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
     they
    -1.20
    感じる
    -1.14
     
    -1.11
    G
    -1.03
     and
    -1.03
    P
    -0.98
    L
    -0.98
     I
    -0.96
    うま
    -0.94
     Hauptstadt
    -0.90
    POSITIVE LOGITS
     paralel
    1.25
    Wymiary
    1.18
     Савез
    1.16
    Recept
    1.16
     måte
    1.13
    徕
    1.13
     سریال
    1.09
    ogonal
    1.09
     number
    1.09
    延伸閱讀
    1.09
    Activations Density 0.011%

    No Known Activations