© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38770
    Prev
    Next
    INDEX
    Explanations

    holy water

    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
     considéré
    -1.02
    D
    -0.99
    vább
    -0.98
     تقری
    -0.98
    [::-
    -0.97
     miljö
    -0.97
    ﾚ
    -0.90
     Socio
    -0.90
     вопросы
    -0.89
     Эти
    -0.89
    POSITIVE LOGITS
     restTemplate
    1.12
     habían
    1.00
     realizará
    0.98
     habló
    0.96
     vieron
    0.96
    kurz
    0.96
     some
    0.95
     Bahkan
    0.94
    grafik
    0.94
    "\"
    0.93
    Activations Density 0.011%

    No Known Activations