© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8808
    Prev
    Next
    INDEX
    Explanations

    Respect, public, head, years

    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
     (
    -1.66
    aconda
    -1.56
    :
    -1.42
     [
    -1.36
     Préférences
    -1.30
     even
    -1.29
    odyne
    -1.25
    opheles
    -1.24
    米国
    -1.23
     даже
    -1.20
    POSITIVE LOGITS
     genoeg
    1.33
     verschill
    1.25
     doesn
    1.23
     вересня
    1.23
     misschien
    1.21
     again
    1.21
    oría
    1.20
     nėra
    1.19
    bigli
    1.19
     dee
    1.18
    Activations Density 0.021%

    No Known Activations