© 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. 15171
    Prev
    Next
    INDEX
    Explanations

    police chief, zerocarbon

    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
     tekno
    -1.34
     teater
    -1.29
     incess
    -1.23
     uan
    -1.23
     pengar
    -1.22
     meren
    -1.19
     spesial
    -1.18
     superbe
    -1.18
     pittores
    -1.18
     conster
    -1.17
    POSITIVE LOGITS
     not
    1.64
    !!
    1.41
    !!!
    1.40
    !
    1.39
    \\
    1.38
     what
    1.36
     now
    1.34
    ↵↵↵
    1.34
     this
    1.32
     often
    1.30
    Activations Density 0.010%

    No Known Activations