© 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. 34-GEMMASCOPE-RES-131K
    7. 1098
    Prev
    Next
    INDEX
    Explanations

    states or processes

    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_34/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
     мы
    -1.26
    Kegiatan
    -1.23
    Catatan
    -1.18
    ℡
    -1.15
    Pengertian
    -1.15
     Kasus
    -1.14
     proteínas
    -1.12
     expliqué
    -1.09
    鏃
    -1.07
     marquées
    -1.06
    POSITIVE LOGITS
     whereby
    1.12
     had
    1.10
     which
    1.08
    NumOf
    1.02
     triumph
    1.02
     resulted
    1.00
     corresponded
    0.98
     been
    0.96
     belonged
    0.96
     requirement
    0.95
    Activations Density 0.057%

    No Known Activations