© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    numbers and labels

    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
    willReturn
    -0.93
    xFFFFFFFF
    -0.93
    クエ
    -0.90
    newArrayList
    -0.88
    ↵↵↵↵↵↵↵↵
    -0.85
     olvides
    -0.84
    ^{}
    -0.84
     向け
    -0.84
    hibits
    -0.80
     natten
    -0.80
    POSITIVE LOGITS
     desu
    0.93
     wygląda
    0.90
    岁的
    0.86
     Substan
    0.84
    顏色
    0.82
     videa
    0.81
     espanhol
    0.81
    jść
    0.81
     subst
    0.80
    gameserver
    0.79
    Activations Density 0.148%

    No Known Activations