© 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. 66306
    Prev
    Next
    INDEX
    Explanations

    steel, weld, seamless, structura, XC

    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
     analis
    -1.37
     francès
    -1.33
    sives
    -1.30
     possible
    -1.26
    packets
    -1.24
    el
    -1.23
    --.
    -1.22
     confirme
    -1.20
    ENDIAN
    -1.19
    isieren
    -1.18
    POSITIVE LOGITS
    stärke
    1.56
    Crítica
    1.55
    spricht
    1.33
    মান
    1.31
    bestimmung
    1.28
     tampaknya
    1.27
    ございました
    1.27
     masculinity
    1.26
    Yup
    1.24
     localización
    1.23
    Activations Density 0.056%

    No Known Activations