© 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. 10-GEMMASCOPE-RES-131K
    7. 104136
    Prev
    Next
    INDEX
    Explanations

    service, served, Diener

    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_10/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
    缑
    -2.33
     漂亮
    -2.19
    ᷇
    -2.05
    蟶
    -2.05
    ujeme
    -2.03
     profundos
    -2.03
     sklep
    -2.02
     voorbeeld
    -1.99
     好看
    -1.97
    錾
    -1.96
    POSITIVE LOGITS
    This
    2.48
    -"
    2.41
    se
    2.28
    —“
    2.28
     Such
    2.27
    If
    2.27
    h
    2.25
    >
    2.23
    These
    2.22
    ps
    2.20
    Activations Density 0.003%

    No Known Activations