© 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. 22-GEMMASCOPE-RES-131K
    7. 26078
    Prev
    Next
    INDEX
    Explanations

    surnames and titles

    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_22/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
     its
    -1.96
    為に
    -1.84
    ところに
    -1.52
    にします
    -1.52
     esplor
    -1.48
    気がします
    -1.41
     mieszkań
    -1.39
     popolari
    -1.37
    もうすぐ
    -1.37
    今日も
    -1.35
    POSITIVE LOGITS
     who
    2.42
    が
    1.89
    を
    1.80
     (
    1.45
    畝
    1.41
    と
    1.41
    は
    1.38
    曲は
    1.33
    もある
    1.32
    pography
    1.31
    Activations Density 0.054%

    No Known Activations