© 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. 184395
    Prev
    Next
    INDEX
    Explanations

    location names and addresses

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

    multilingual descriptions and stages

    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
    🧾
    0.52
     toppings
    0.50
     descart
    0.49
     commen
    0.48
    ཎ
    0.46
     doesn
    0.45
    ৬০
    0.45
     calculations
    0.45
     citizen
    0.45
     parmes
    0.45
    POSITIVE LOGITS
    urbed
    0.53
    س
    0.49
    zerw
    0.47
    朝
    0.46
    在北京
    0.46
    url
    0.46
    ي
    0.46
    riwal
    0.44
    prevState
    0.43
     বাঁধ
    0.43
    Activations Density 0.000%

    No Known Activations