© 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. 86442
    Prev
    Next
    INDEX
    Explanations

    substantially, overall, expected

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

    range between

    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
    。
    0.57
    掠
    0.50
    タニ
    0.50
    չ
    0.49
    前方
    0.48
    娘
    0.48
    م
    0.47
    ጠ
    0.47
    ев
    0.45
    פ
    0.45
    POSITIVE LOGITS
     együtt
    0.48
     Convolution
    0.48
     Drinking
    0.48
     சுற்றுச்சூழல்
    0.46
     ünlü
    0.46
     interconnect
    0.45
     Wetlands
    0.45
     Functions
    0.45
     শিল্প
    0.44
     Dependency
    0.44
    Activations Density 0.001%

    No Known Activations