© 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. 99476
    Prev
    Next
    INDEX
    Explanations

    ongoing action or state after been

    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
     одному
    -1.51
     begrenzt
    -1.40
    soo
    -1.39
     gemessen
    -1.37
    metido
    -1.34
     tabPage
    -1.34
    šia
    -1.30
    ようで
    -1.29
    どもの
    -1.28
    ⤦
    -1.28
    POSITIVE LOGITS
     in
    1.74
     This
    1.47
     It
    1.40
     These
    1.38
    anguardia
    1.38
     epistem
    1.37
    there
    1.34
    itars
    1.32
    this
    1.31
     You
    1.29
    Activations Density 0.025%

    No Known Activations