© 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. 15101
    Prev
    Next
    INDEX
    Explanations

    words following "with"

    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
     or
    -1.76
     while
    -1.52
    😤
    -1.44
     vergeten
    -1.43
    🤙
    -1.42
     in
    -1.35
     which
    -1.34
    😇
    -1.33
    ;;)
    -1.32
    жнарод
    -1.32
    POSITIVE LOGITS
     lots
    2.50
     a
    2.30
     plenty
    2.28
     no
    1.70
     loads
    1.67
     even
    1.50
    よろしくお願いします
    1.49
    Lots
    1.48
     nhiều
    1.47
     little
    1.42
    Activations Density 0.053%

    No Known Activations