© 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. 149006
    Prev
    Next
    INDEX
    Explanations

    internet domains and paths

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

    .com/ or .au/ URLs

    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
     nanot
    0.50
     hủy
    0.48
    鴟
    0.46
     automobiles
    0.45
     vaults
    0.45
     hydraulic
    0.45
     whanne
    0.43
     wicket
    0.43
     naph
    0.43
     solar
    0.43
    POSITIVE LOGITS
    /...
    0.51
    小组
    0.49
    ouncil
    0.48
    appendix
    0.47
    lebr
    0.46
    ...</
    0.46
    Лю
    0.46
    ...(
    0.44
    Putin
    0.44
    quotes
    0.44
    Activations Density 0.017%

    No Known Activations