© 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. 22-GEMMASCOPE-RES-131K
    7. 14282
    Prev
    Next
    INDEX
    Explanations

    legal citations and technical commands

    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
     that
    -1.12
     najwięks
    -1.09
     its
    -1.05
     various
    -1.03
    嫱
    -1.01
     cinza
    -1.00
     verschill
    -0.97
     these
    -0.96
    </h5>
    -0.95
    ookie
    -0.95
    POSITIVE LOGITS
    星空
    1.23
    eniu
    1.19
    や
    1.14
     Facult
    1.13
    Recept
    1.12
    uestran
    1.11
     незавер
    1.09
     Multip
    1.09
     Additive
    1.09
    ENTION
    1.07
    Activations Density 0.003%

    No Known Activations