© 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. 1117
    Prev
    Next
    INDEX
    Explanations

    introductory phrases

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

    generative retrieval methods

    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
    0.64
    ?
    0.63
    that
    0.62
     あなた
    0.59
     you
    0.58
     as
    0.57
    canada
    0.57
    th
    0.56
    _
    0.55
    ky
    0.55
    POSITIVE LOGITS
     voltmeter
    0.54
     typographic
    0.54
     chronograph
    0.52
     microbiological
    0.50
     muon
    0.50
     multidiscipl
    0.50
     chromatographic
    0.50
     உட்பட
    0.49
     কাঠের
    0.49
     theologian
    0.48
    Activations Density 0.395%

    No Known Activations