© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1080
    Prev
    Next
    INDEX
    Explanations

    yr after

    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
    !
    -1.32
     melainkan
    -1.32
    !”
    -1.29
     tiroirs
    -1.27
    .”
    -1.26
    rightarrow
    -1.24
     behalf
    -1.23
    ⬍
    -1.23
    Tiene
    -1.22
     merkwür
    -1.21
    POSITIVE LOGITS
     the
    1.58
    Wymiary
    1.27
     Administración
    1.20
     menyadari
    1.14
     revolución
    1.13
     they
    1.11
     bepaalde
    1.10
     not
    1.09
    まき
    1.08
     Resolución
    1.08
    Activations Density 0.293%

    No Known Activations