© 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. 34188
    Prev
    Next
    INDEX
    Explanations

    Simplify math expressions

    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
    橹
    -1.32
    ᕮ
    -1.15
     Onze
    -1.15
     vertus
    -1.11
     違い
    -1.10
     lauded
    -1.07
    嗵
    -1.07
    ꯰
    -1.04
     lorsqu
    -1.02
     revered
    -1.02
    POSITIVE LOGITS
     and
    1.32
     after
    1.02
     at
    1.01
     actively
    1.00
     give
    0.93
     uses
    0.93
     causing
    0.93
     luckily
    0.93
     especially
    0.93
     initially
    0.93
    Activations Density 0.092%

    No Known Activations