© 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. 64718
    Prev
    Next
    INDEX
    Explanations

    who followed by a verb phrase

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

    who followed by a 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
    的主要
    0.49
    ת
    0.49
    やつ
    0.46
    లు
    0.45
     autorità
    0.44
     údaj
    0.44
     hallmarks
    0.44
     outcast
    0.44
     supporters
    0.43
     tvrd
    0.43
    POSITIVE LOGITS
     selaku
    0.55
    ée
    0.50
    0
    0.50
    ?
    0.48
    ^{*}
    0.47
    tm
    0.47
    bs
    0.47
    az
    0.46
    Era
    0.46
    였습니다
    0.45
    Activations Density 0.021%

    No Known Activations