© 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. 3598
    Prev
    Next
    INDEX
    Explanations

    that followed by pronoun or article

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

    after comma

    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
    而在
    0.23
    那我們
    0.20
    愺
    0.20
    ੪
    0.20
     किंतु
    0.20
     égales
    0.19
    ్
    0.19
     கெல்
    0.19
     근데
    0.19
    而
    0.19
    POSITIVE LOGITS
     it
    0.33
     this
    0.28
     the
    0.26
     there
    0.23
    this
    0.22
    0.22
    the
    0.22
     each
    0.22
     The
    0.22
     these
    0.21
    Activations Density 0.622%

    No Known Activations