© 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. 102858
    Prev
    Next
    INDEX
    Explanations

    generally to

    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
    Bahkan
    -1.42
     it
    -1.36
    Kelebihan
    -1.34
     which
    -1.29
    Mereka
    -1.28
    Setiap
    -1.27
     memutus
    -1.26
     this
    -1.26
    Sebelum
    -1.25
     isles
    -1.24
    POSITIVE LOGITS
     to
    2.59
     of
    2.13
     into
    1.55
     \
    1.46
     čia
    1.43
     again
    1.41
     about
    1.40
     crucial
    1.33
     on
    1.31
     pero
    1.30
    Activations Density 0.203%

    No Known Activations