© 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. 26402
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
     первым
    -1.20
     incluye
    -1.18
     before
    -1.16
     but
    -1.14
    )<=
    -1.13
    일에
    -1.12
     empezaron
    -1.12
     ofrece
    -1.11
     jonge
    -1.11
     déput
    -1.09
    POSITIVE LOGITS
     life
    1.27
     akade
    1.23
     translateY
    1.20
     Konkur
    1.17
     better
    1.14
    
    1.13
    Жизнь
    1.12
    станов
    1.08
    が必要です
    1.08
    自己
    1.07
    Activations Density 0.023%

    No Known Activations