© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4473
    Prev
    Next
    INDEX
    Explanations

    wyman, teamwork, personal, human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ტის
    0.35
     የተለያዩ
    0.35
    菲律
    0.34
    椿
    0.34
     ಔಷಧ
    0.34
    Miscellaneous
    0.33
    П
    0.33
    პ
    0.32
    अर
    0.32
    Colorful
    0.32
    POSITIVE LOGITS
     manned
    0.44
     ανθρώ
    0.43
     teamwork
    0.38
     лично
    0.37
     mammalian
    0.36
     Wyman
    0.36
     personales
    0.35
     Murder
    0.35
     dành
    0.34
     personnelles
    0.34
    Activations Density 0.953%

    No Known Activations