© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 120603
    Prev
    Next
    INDEX
    Explanations

    free trial and time to kill

    np_acts-logits-general · gemini-2.5-flash-lite

    adjectives modifying nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arı
    0.50
    名の
    0.45
    )})
    0.44
    это
    0.43
     Л
    0.42
     responsável
    0.42
    тном
    0.42
    Чтобы
    0.42
     desempenho
    0.40
    ஜ்மஹால்
    0.40
    POSITIVE LOGITS
     Remix
    0.48
    woocommerce
    0.46
     ب
    0.46
     प्रिपरेशन
    0.46
    etsa
    0.46
     भजन
    0.45
    uvi
    0.44
     বিনি
    0.44
     Premiership
    0.44
    ett
    0.44
    Activations Density 0.000%

    No Known Activations