© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130408
    Prev
    Next
    INDEX
    Explanations

    numbers in sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -1.44
    他已经
    -1.23
    にあります
    -1.23
    Everything
    -1.22
     to
    -1.22
     in
    -1.17
    ܜ
    -1.16
    TestingModule
    -1.13
    今度は
    -1.12
    今から
    -1.12
    POSITIVE LOGITS
     and
    1.37
    kese
    1.28
     कई
    1.19
    owm
    1.19
    nere
    1.18
    stadion
    1.13
    cember
    1.12
    นี้
    1.11
    を
    1.09
     maioria
    1.08
    Activations Density 0.026%

    No Known Activations