© 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-16K
    7. 11787
    Prev
    Next
    INDEX
    Explanations

    human

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

    human spirit, cost, rights

    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_16k_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
    is
    0.79
    l
    0.59
     உள்ளட
    0.58
    m
    0.58
    م
    0.58
    of
    0.54
    p
    0.53
    k
    0.52
    ллер
    0.49
    ل
    0.49
    POSITIVE LOGITS
     human
    1.39
     manusia
    1.36
     Human
    1.34
    Human
    1.31
     humain
    1.31
     humaine
    1.30
     humana
    1.30
     HUMAN
    1.26
     umano
    1.23
     челове
    1.23
    Activations Density 0.112%

    No Known Activations