© 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. 15527
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     kepolisian
    -1.22
    你的
    -1.21
    有很多
    -1.16
    How
    -1.11
    Podob
    -1.10
     organizza
    -1.08
    Why
    -1.07
    ol
    -1.07
     njego
    -1.06
     Reised
    -1.06
    POSITIVE LOGITS
    vább
    1.29
     ilustracji
    1.22
     eſ
    1.20
    lified
    1.16
     iyon
    1.11
    xffffffff
    1.09
     bolsillos
    1.09
    \<
    1.09
    häuse
    1.06
    rpg
    1.05
    Activations Density 0.717%

    No Known Activations