© 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. 44492
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and locations

    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
     menik
    -1.41
     ondu
    -1.30
     custodia
    -1.23
     consumi
    -1.23
    ).—
    -1.23
     Europeo
    -1.23
     masaj
    -1.21
     multa
    -1.21
     molesta
    -1.20
     beneficia
    -1.20
    POSITIVE LOGITS
     своего
    1.16
     ebenso
    1.10
    Its
    1.09
    相同
    1.05
    ปัญ
    1.04
    romeo
    1.03
    I
    1.03
    You
    1.03
    Neither
    1.02
     его
    1.02
    Activations Density 0.405%

    No Known Activations