© 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. 15889
    Prev
    Next
    INDEX
    Explanations

    `pb(`, `printf(`, `MAX`)`

    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
     Optionen
    -1.16
     aplikacji
    -1.16
     acesso
    -1.15
     コミック
    -1.13
     polska
    -1.13
    และ
    -1.13
     guantes
    -1.13
     Komponenten
    -1.13
     warszawa
    -1.11
     dispozici
    -1.10
    POSITIVE LOGITS
     after
    1.27
     OGSÅ
    1.18
    After
    1.17
     Especially
    1.08
    どちらも
    1.05
    Both
    1.03
     can
    1.02
     zarówno
    1.02
     после
    1.02
    ecore
    1.02
    Activations Density 0.005%

    No Known Activations