© 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. 15136
    Prev
    Next
    INDEX
    Explanations

    Zombie Seinfeld

    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
     Gastgeber
    -1.30
     ちゃん
    -1.26
    Zeneca
    -1.23
     our
    -1.22
     упражнения
    -1.18
     katholischen
    -1.14
     we
    -1.11
    iveau
    -1.09
     Städ
    -1.08
     Pfar
    -1.05
    POSITIVE LOGITS
     you
    2.08
     você
    1.50
     your
    1.38
     вам
    1.35
    Kepala
    1.20
    пресс
    1.14
    Mereka
    1.12
     menghubungi
    1.12
     menetap
    1.11
    讫
    1.11
    Activations Density 0.034%

    No Known Activations