© 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. 10-GEMMASCOPE-RES-131K
    7. 60529
    Prev
    Next
    INDEX
    Explanations

    joined school year

    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
     miliar
    -1.40
     grammi
    -1.38
     keindahan
    -1.30
     across
    -1.24
     kwamba
    -1.23
     потом
    -1.23
     kabupaten
    -1.22
    голо
    -1.20
     this
    -1.19
     throughout
    -1.19
    POSITIVE LOGITS
     its
    1.49
    에서
    1.45
     where
    1.36
     العمل
    1.23
     حيث
    1.22
    ției
    1.20
    らを
    1.18
    着一个
    1.16
    での
    1.15
    אני
    1.15
    Activations Density 0.090%

    No Known Activations