© 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. 72478
    Prev
    Next
    INDEX
    Explanations

    International events and organizations

    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
    などを
    -1.30
    などが
    -1.16
    が
    -1.15
    还得
    -1.11
     prachtige
    -1.09
     ausreichend
    -1.09
    いを
    -1.07
     Zutaten
    -1.06
     stycznia
    -1.04
     الجلد
    -1.04
    POSITIVE LOGITS
     So
    0.94
    総評
    0.93
    ところは
    0.92
    líben
    0.92
    Diario
    0.90
     and
    0.85
    Some
    0.85
    BIÉN
    0.85
     pronti
    0.84
    seins
    0.84
    Activations Density 0.059%

    No Known Activations