© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19979
    Prev
    Next
    INDEX
    Explanations

    mailbox, home, locker

    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_10/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
    -1.85
    true
    -1.33
     actually
    -1.30
     necessary
    -1.16
     indeed
    -1.12
    ﹕
    -1.04
    attr
    -1.04
    unique
    -1.02
     yeah
    -1.02
    shi
    -1.02
    POSITIVE LOGITS
     óptica
    1.27
    RAI
    1.16
    obedience
    1.16
    Với
    1.10
    mueble
    1.09
    Overwatch
    1.08
    赃
    1.06
     cápsulas
    1.05
     zowel
    1.05
    Hebrews
    1.05
    Activations Density 0.101%

    No Known Activations