© 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. 22-GEMMASCOPE-RES-131K
    7. 34339
    Prev
    Next
    INDEX
    Explanations

    industries and artificial intelligence

    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_22/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
     estuche
    -1.52
    komplet
    -1.50
     motocicletas
    -1.46
    ὴν
    -1.44
     montañas
    -1.38
     ruinas
    -1.38
     fikk
    -1.38
     pasaba
    -1.37
    gör
    -1.33
    subseteq
    -1.32
    POSITIVE LOGITS
    :
    1.62
     such
    1.58
     data
    1.42
     Data
    1.39
     faster
    1.29
    i
    1.29
     better
    1.26
     like
    1.25
     Lese
    1.25
     can
    1.24
    Activations Density 0.028%

    No Known Activations