© 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. 10-GEMMASCOPE-RES-131K
    7. 99117
    Prev
    Next
    INDEX
    Explanations

    various topics and entities

    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_10/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
    ⟞
    -1.39
     mooie
    -1.36
    𓆏
    -1.34
     "
    -1.29
     '"
    -1.26
    processes
    -1.23
     "'
    -1.22
     your
    -1.20
    PropertyChanged
    -1.20
     merve
    -1.19
    POSITIVE LOGITS
     especially
    1.48
     to
    1.35
     Numerous
    1.33
     Especially
    1.28
     навіть
    1.27
     Regardless
    1.26
     Specifically
    1.24
    Numerous
    1.23
     at
    1.23
    Often
    1.22
    Activations Density 0.194%

    No Known Activations