© 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. 2318
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    pronoun followed by auxiliary verb

    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
    NOWLEDGE
    0.29
     แล้ว
    0.29
    𝗬
    0.28
    RESULT
    0.27
     delineation
    0.26
     supposing
    0.25
     extracting
    0.25
     తమ
    0.25
     จง
    0.25
     ውጤ
    0.25
    POSITIVE LOGITS
     can
    0.39
     is
    0.36
     had
    0.35
     are
    0.34
     have
    0.33
    ’
    0.31
     got
    0.30
     will
    0.30
     came
    0.29
     didn
    0.29
    Activations Density 1.012%

    No Known Activations