© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34989
    Prev
    Next
    INDEX
    Explanations

    causal inference and study designs

    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
     noche
    -1.18
     importants
    -1.17
    ׇ
    -1.16
     frigo
    -1.16
     anormal
    -1.15
    🖐
    -1.15
    зин
    -1.14
     fraiche
    -1.13
     estime
    -1.12
     vernis
    -1.11
    POSITIVE LOGITS
     test
    1.23
     бампер
    1.23
    ombus
    1.23
    ֶּ
    1.20
     study
    1.19
     methodology
    1.16
    じゃなくて
    1.15
     zesta
    1.13
     Políticas
    1.12
     case
    1.10
    Activations Density 0.055%

    No Known Activations