© 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. 71371
    Prev
    Next
    INDEX
    Explanations

    linking two things

    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
     senza
    -1.48
     пър
    -1.41
     and
    -1.38
    ",
    -1.37
     ohne
    -1.32
    .
    -1.30
     první
    -1.30
     zonder
    -1.25
     vijf
    -1.24
    ladelphia
    -1.21
    POSITIVE LOGITS
    zesse
    1.35
     fjor
    1.34
     another
    1.33
     concernés
    1.30
     ポート
    1.27
     champions
    1.23
     groundbreaking
    1.22
     regularly
    1.20
     equipment
    1.20
    tą
    1.20
    Activations Density 0.056%

    No Known Activations