© 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. 39703
    Prev
    Next
    INDEX
    Explanations

    material, oil, tiles, blisters, flowers

    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
     in
    -1.98
     on
    -1.63
     let
    -1.43
     it
    -1.38
     this
    -1.34
    들에게
    -1.30
    スムーズ
    -1.27
     tohto
    -1.27
    ↵↵
    -1.23
     but
    -1.21
    POSITIVE LOGITS
    ୌ
    1.90
    勦
    1.42
     "",
    1.38
    AGEMENT
    1.38
    thema
    1.37
    iteit
    1.35
    ଃ
    1.34
    %).
    1.34
     "").
    1.33
     anún
    1.32
    Activations Density 0.161%

    No Known Activations