© 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. 173071
    Prev
    Next
    INDEX
    Explanations

    measurements followed by selections

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

    "are", "am", "is" auxiliary verbs

    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
    ermanfaat
    0.50
    ấc
    0.48
     моз
    0.47
    ítom
    0.46
     hypothalamic
    0.46
     프로그램을
    0.45
    肐
    0.45
    otene
    0.45
     ক্যাল
    0.45
     これらの
    0.45
    POSITIVE LOGITS
    W
    0.57
     Bars
    0.50
    H
    0.50
    B
    0.49
    P
    0.48
    T
    0.46
     Business
    0.45
    Business
    0.45
     cid
    0.45
    BUT
    0.45
    Activations Density 0.000%

    No Known Activations