© 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. 38654
    Prev
    Next
    INDEX
    Explanations

    conditional statements and definitions

    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
     $-.
    -0.88
     portail
    -0.87
    backen
    -0.83
    preferably
    -0.82
     様子
    -0.82
    منم
    -0.82
    ्न
    -0.81
     ARY
    -0.81
     Conseils
    -0.80
    馳走
    -0.80
    POSITIVE LOGITS
     if
    2.06
     when
    1.65
     dacă
    1.28
     iff
    1.27
     если
    1.25
     apabila
    1.24
     akkor
    1.19
     jeśli
    1.17
     cuando
    1.15
     jeżeli
    1.15
    Activations Density 0.045%

    No Known Activations