© 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-16K
    7. 12453
    Prev
    Next
    INDEX
    Explanations

    .ItsWeIfItsTheseAndsmallThese

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

    SQL LIKE clauses and specific titles

    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_16k_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
    從
    0.60
    ，
    0.58
    ،
    0.57
     DBox
    0.56
     que
    0.55
    、
    0.55
     從
    0.54
    ي
    0.53
    ͯ
    0.53
    ઁ
    0.51
    POSITIVE LOGITS
     없다
    0.44
     ไม่มี
    0.43
    щают
    0.42
     створе
    0.42
    lardır
    0.41
    <unused53>
    0.40
    辫
    0.40
     юк
    0.40
     encir
    0.40
     отдела
    0.39
    Activations Density 0.005%

    No Known Activations