© 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. 202355
    Prev
    Next
    INDEX
    Explanations

    stationery and New Zealand Maori

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

    clarity and specification

    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
    sli
    0.51
    薛
    0.49
    uno
    0.49
    opin
    0.48
    NN
    0.47
    N
    0.47
    slo
    0.47
    s
    0.47
    URANCE
    0.46
    sixth
    0.46
    POSITIVE LOGITS
     Stationery
    0.50
    თვის
    0.48
     souha
    0.46
    に向け
    0.45
     Supplied
    0.44
    atein
    0.44
     bhikkhu
    0.43
     निश्चित
    0.43
     Basics
    0.42
     stationery
    0.42
    Activations Density 0.000%

    No Known Activations