© 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. 65400
    Prev
    Next
    INDEX
    Explanations

    American education, normal human

    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
    🪙
    -1.20
    stwo
    -1.19
    ofas
    -1.16
     cirugía
    -1.15
    ocarditis
    -1.14
     کردی
    -1.14
    AndWait
    -1.12
    Minist
    -1.11
    蛊
    -1.10
     ventilación
    -1.09
    POSITIVE LOGITS
     сахара
    1.67
     often
    1.33
     ویتامین
    1.17
     study
    1.15
    𝗺
    1.14
    cdot
    1.10
     ersten
    1.10
     通販
    1.09
     дошко
    1.09
     needed
    1.08
    Activations Density 0.011%

    No Known Activations