© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16406
    Prev
    Next
    INDEX
    Explanations

    fiscal Q1

    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
     our
    -1.66
     pertaining
    -1.20
    🪙
    -1.17
     regarding
    -1.16
    strictEqual
    -1.14
     decorative
    -1.10
    ？！”
    -1.09
     solteiro
    -1.09
     these
    -1.07
     osv
    -1.05
    POSITIVE LOGITS
     vão
    1.21
     entweder
    1.17
     einerseits
    1.16
     estão
    1.16
     用于
    1.14
     🤣
    1.13
    imee
    1.12
    madeus
    1.08
     Siamo
    1.07
    进攻
    1.06
    Activations Density 0.027%

    No Known Activations