© 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. 39929
    Prev
    Next
    INDEX
    Explanations

    Kubernetes resource names and configurations

    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
    .
    -1.39
     słucha
    -1.31
    わたしは
    -1.30
     scris
    -1.29
     palsu
    -1.28
     receber
    -1.28
    0
    -1.27
    i
    -1.25
     otwor
    -1.24
    ية
    -1.23
    POSITIVE LOGITS
     jubile
    1.55
    してくれた
    1.46
     Condiciones
    1.38
    iplin
    1.36
     gracios
    1.32
     behövs
    1.32
     onData
    1.31
    ਲ਼
    1.31
    gazione
    1.30
     muy
    1.29
    Activations Density 0.041%

    No Known Activations