© 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. 8304
    Prev
    Next
    INDEX
    Explanations

    Q following code tokens

    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
     new
    -2.16
     who
    -2.08
     one
    -1.98
     people
    -1.91
     Unlike
    -1.88
     helps
    -1.86
     type
    -1.84
     serves
    -1.84
     this
    -1.83
    fatto
    -1.82
    POSITIVE LOGITS
    箧
    1.96
     烤
    1.88
    рованной
    1.84
    一款
    1.80
     problemet
    1.80
     silueta
    1.74
     alltid
    1.73
     极
    1.73
    als
    1.72
    盉
    1.71
    Activations Density 0.000%

    No Known Activations