© 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. 9529
    Prev
    Next
    INDEX
    Explanations

    formal nouns ending in -tion or -sion

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

    actions ending in ation

    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
    ના
    0.75
    い
    0.69
    د
    0.65
    あ
    0.65
     ruangan
    0.63
    見
    0.63
    I
    0.63
     muut
    0.62
    માં
    0.61
     představ
    0.61
    POSITIVE LOGITS
    is
    1.16
    x
    1.13
    us
    0.89
    ти
    0.87
    ق
    0.84
    ле
    0.81
    tr
    0.79
    n
    0.77
    an
    0.76
    ’
    0.73
    Activations Density 0.730%

    No Known Activations