© 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. 128653
    Prev
    Next
    INDEX
    Explanations

    ideas about things

    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
     scel
    -1.34
    ↵
    -1.34
     diseñados
    -1.33
    㩒
    -1.16
    킁
    -1.13
     そば
    -1.13
     perche
    -1.12
    ANCED
    -1.12
    ㍑
    -1.09
    those
    -1.09
    POSITIVE LOGITS
     ideas
    1.43
     Usually
    1.20
     There
    1.19
    .
    1.18
     It
    1.13
     Since
    1.09
     keeps
    1.09
     Although
    1.08
     Sadly
    1.05
    倣
    1.04
    Activations Density 0.028%

    No Known Activations