© 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. 65054
    Prev
    Next
    INDEX
    Explanations

    setting, adding, defining, pasting

    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
     to
    -1.28
     diesmal
    -1.08
     therefore
    -1.08
     how
    -1.07
     health
    -1.05
     everything
    -1.05
     other
    -1.05
     for
    -1.04
     هذه
    -1.01
     things
    -1.00
    POSITIVE LOGITS
     соответству
    1.16
     with
    1.12
     április
    1.11
     jednod
    1.10
    핌
    1.08
     either
    1.08
     simplement
    1.06
     zostanie
    1.06
     любы
    1.05
     behov
    1.05
    Activations Density 0.084%

    No Known Activations