© 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. 92035
    Prev
    Next
    INDEX
    Explanations

    words ending phrases

    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
    色々な
    -1.34
    importante
    -1.27
    Similar
    -1.24
     africaine
    -1.16
    色々
    -1.15
    色んな
    -1.13
    Kegiatan
    -1.12
    で大
    -1.10
    綺麗な
    -1.09
    パパ
    -1.09
    POSITIVE LOGITS
     that
    3.58
     of
    3.00
     που
    2.05
     which
    2.02
     الذي
    1.52
     whose
    1.52
    ที่
    1.48
     who
    1.44
     که
    1.42
    ของ
    1.26
    Activations Density 0.010%

    No Known Activations