© 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. 34-GEMMASCOPE-RES-131K
    7. 87082
    Prev
    Next
    INDEX
    Explanations

    conception and research contributions

    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
    ➩
    -0.97
     terkenal
    -0.94
     sezonu
    -0.85
     popolari
    -0.84
     concluyó
    -0.83
     menunjukkan
    -0.82
    ངས་
    -0.82
    使用
    -0.82
     subió
    -0.82
    ございます
    -0.81
    POSITIVE LOGITS
     conception
    1.74
     conceived
    1.44
     conceptual
    1.41
     critically
    1.23
     drafting
    1.20
     acquisition
    1.19
    conception
    1.18
     conceive
    1.16
     Conception
    1.12
    concept
    1.09
    Activations Density 0.020%

    No Known Activations