© 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. 172685
    Prev
    Next
    INDEX
    Explanations

    invited guests, Hull backdrop, different challenge, amusing way

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

    selling products

    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
    槤
    0.52
     nevoia
    0.52
     ôn
    0.47
     olímp
    0.47
     Obsidian
    0.47
     來
    0.47
    പരമായ
    0.46
    穵
    0.46
    אה
    0.46
     கிட
    0.46
    POSITIVE LOGITS
    terror
    0.48
     metric
    0.48
    0
    0.48
    els
    0.47
     physicochemical
    0.46
     millimeter
    0.46
     colored
    0.45
    metric
    0.45
    2
    0.45
    textured
    0.45
    Activations Density 0.002%

    No Known Activations