© 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. 22-GEMMASCOPE-RES-131K
    7. 130726
    Prev
    Next
    INDEX
    Explanations

    verbs of speaking

    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
     which
    -1.24
     and
    -1.17
     likely
    -1.03
     who
    -1.02
    この辺
    -0.96
     "[
    -0.94
     alrededores
    -0.94
    無し
    -0.94
    起了
    -0.93
     létre
    -0.93
    POSITIVE LOGITS
    ว่า
    1.27
    ȝ
    1.00
     then
    0.99
    ayı
    0.98
    aż
    0.98
    yeh
    0.96
     nxt
    0.96
     nochmals
    0.94
     tantum
    0.94
    oara
    0.94
    Activations Density 0.011%

    No Known Activations