© 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. 10-GEMMASCOPE-RES-131K
    7. 85734
    Prev
    Next
    INDEX
    Explanations

    potential outcomes and risks

    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
     to
    -2.64
     such
    -1.57
     its
    -1.52
     are
    -1.51
     being
    -1.50
     consume
    -1.47
     it
    -1.46
     needing
    -1.41
    يار
    -1.38
     either
    -1.38
    POSITIVE LOGITS
     нашего
    1.69
    蕯
    1.57
    Those
    1.48
     brasileiro
    1.48
    殁
    1.46
    Sejarah
    1.44
    情节
    1.44
    岘
    1.43
     этого
    1.42
     américain
    1.41
    Activations Density 0.239%

    No Known Activations