© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    .com, questions, operator

    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
     has
    -1.45
     دیگری
    -1.43
    って感じ
    -1.41
     other
    -1.38
    着一个
    -1.36
    /
    -1.35
     AssemblyCulture
    -1.34
     напомина
    -1.34
    だよね
    -1.33
    って思
    -1.33
    POSITIVE LOGITS
     they
    1.73
     они
    1.65
     даже
    1.63
    both
    1.55
    even
    1.52
    ↵
    1.38
    詬
    1.35
     aunque
    1.32
     если
    1.31
    iforme
    1.30
    Activations Density 0.098%

    No Known Activations