© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71872
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions and adverbs

    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
    くださった
    -1.60
     confronti
    -1.56
     those
    -1.56
    蓁
    -1.40
     with
    -1.40
    acea
    -1.39
    顳
    -1.38
    usura
    -1.36
    所说的
    -1.34
     siap
    -1.33
    POSITIVE LOGITS
    了一
    2.11
     was
    1.64
    一名
    1.50
    ,
    1.45
     demean
    1.44
    ᪥
    1.44
     wouldn
    1.42
    两
    1.39
     would
    1.37
    𝗲
    1.37
    Activations Density 0.028%

    No Known Activations