© 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. 121358
    Prev
    Next
    INDEX
    Explanations

    is are and equivalents

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

    what is / what are

    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
    is
    0.89
    as
    0.83
    at
    0.82
    it
    0.79
    ’
    0.73
    K
    0.67
    e
    0.62
    ie
    0.61
    ти
    0.61
    ه
    0.60
    POSITIVE LOGITS
     is
    1.00
    ，
    0.91
     của
    0.87
     ของ
    0.81
    ของ
    0.81
    の
    0.78
     OF
    0.75
    larının
    0.74
     ﺍﻟ
    0.74
    的
    0.73
    Activations Density 0.421%

    No Known Activations